Smooth jagged sub-national region boundaries (v0.16.0)
CI / build + unit + e2e (pull_request) Successful in 2m18s
CI / build + unit + e2e (pull_request) Successful in 2m18s
Part of #16
This commit is contained in:
@@ -404,4 +404,40 @@ describe('regions.geo.json', () => {
|
||||
` / max ${maxId} ${(100 * maxRatio).toFixed(1)}% (band 40–175%)`,
|
||||
);
|
||||
});
|
||||
|
||||
it('is at the Douglas–Peucker 50m fixed point: 1,796 regions, topology unchanged, 111,175 vertices (v0.16 smoothing)', () => {
|
||||
// v0.16 (scripts/smooth-regions.mjs) thinned every ring with Douglas–Peucker at
|
||||
// ~50 m. That removes redundant vertices only — it never moves a border, merges
|
||||
// a part, or creates/removes a ring — so the topology signature is invariant
|
||||
// (1,796 features, 5,026 parts, 5,027 rings, the single KZ-KZY hole) and the
|
||||
// vertex total sits at the pass's fixed point (re-running changes nothing).
|
||||
// Pinning it guards against an accidental re-coarsening or a different-tolerance
|
||||
// re-smooth silently changing the shipped dataset.
|
||||
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(1796);
|
||||
expect(verts, 'total vertices (incl. ring closure)').toBe(111_175); // was 111,891 pre-v0.16; 716 removed
|
||||
expect(parts, 'parts').toBe(5026); // unchanged — no part merged/dropped
|
||||
expect(rings, 'rings').toBe(5027); // unchanged — no ring added/dropped
|
||||
expect(holes, 'holes').toBe(1); // the single KZ-KZY hole, unchanged
|
||||
expect(holeIds, 'the one remaining hole is KZ-KZY').toEqual(['KZ-KZY']);
|
||||
console.log(
|
||||
`\n v0.16 smoothing: ${regions.features.length} regions, ${parts} parts, ${rings} rings, ` +
|
||||
`${holes} hole (KZ-KZY), ${verts} vertices (50m DP fixed point; 716 removed from 111,891) — topology unchanged`,
|
||||
);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -0,0 +1,180 @@
|
||||
#!/usr/bin/env node
|
||||
/**
|
||||
* scripts/smooth-regions.mjs — smooths jagged sub-national region boundaries.
|
||||
*
|
||||
* Run: npm run smooth:regions (in place on public/regions.geo.json)
|
||||
* node scripts/smooth-regions.mjs [out] [src]
|
||||
*
|
||||
* The v0.14 coarsening (boolean dissolve) and Natural Earth's 1:10m digitization
|
||||
* left some sub-national boundaries overly jagged — the worst being coastal /
|
||||
* borderland regions that the dissolve split into many small, zig-zag fragments
|
||||
* (e.g. SI-048 Kocevje, Slovenia, 57 parts; MK-36 Kavadartsi, N. Macedonia, 8
|
||||
* parts). This cleans the jaggedness in place with **Douglas–Peucker
|
||||
* vertex-thinning** (`@turf/simplify`), applied to every ring of every polygon.
|
||||
*
|
||||
* DOUGLAS–PEUCKER — `@turf/simplify` keeps a vertex only when it deviates from
|
||||
* the chord joining its kept neighbours by more than the tolerance, removing
|
||||
* the redundant "in-between" points of a shallow zig-zag. The tolerance is
|
||||
* expressed in the GeoJSON degree space (its distance metric treats 1° lon
|
||||
* == 1° lat); TOLERANCE_M (metres) is converted with the same ~111 km/° the
|
||||
* area model uses, so TOLERANCE_M = 50 is a gentle ~50 m pass. Bump it to
|
||||
* 100 / 200 for a stronger pass and re-run — the pass is idempotent either way.
|
||||
*
|
||||
* VERTEX-THINNING ONLY — DP only removes points. It never moves a border,
|
||||
* never merges/dissolves regions or parts, and never creates or removes a
|
||||
* ring, so topology is preserved exactly: the region count, every `id`,
|
||||
* `properties.name`/`properties.parent`, the part count of every feature, the
|
||||
* single real hole (KZ-KZY), and all 83 islands are all unchanged. Only the
|
||||
* redundant vertices along each ring are dropped.
|
||||
*
|
||||
* Deterministic + idempotent: one @turf/simplify pass at a fixed tolerance, then
|
||||
* 4-dp rounding (the same convention as the other scripts). Because the output
|
||||
* is already at the tolerance's fixed point, re-running on the smoothed file
|
||||
* yields a byte-identical file (sha256-verified). The 18 degenerate 3-point
|
||||
* micro-rings (the ~0-area "dots" like Ragged Island / the Paracels) are kept
|
||||
* verbatim — @turf/simplify requires ≥4 points and would otherwise throw — so
|
||||
* no ring is ever dropped and every feature keeps its exact part/ring count.
|
||||
*/
|
||||
|
||||
import { readFileSync, writeFileSync } from 'node:fs';
|
||||
import path from 'node:path';
|
||||
import { fileURLToPath } from 'node:url';
|
||||
import { simplify } from '@turf/simplify';
|
||||
|
||||
const here = path.dirname(fileURLToPath(import.meta.url));
|
||||
const root = path.resolve(here, '..');
|
||||
const DEFAULT_FILE = path.join(root, 'public', 'regions.geo.json');
|
||||
const args = process.argv.slice(2).filter((a) => !a.startsWith('-'));
|
||||
const OUT = args[0] ? path.resolve(args[0]) : DEFAULT_FILE;
|
||||
const SRC = args[1] ? path.resolve(args[1]) : DEFAULT_FILE;
|
||||
|
||||
// --- parameters ---------------------------------------------------------------
|
||||
const TOLERANCE_M = 50; // DP tolerance in metres — ~50 m is gentle (bump to 100/200 for more)
|
||||
const M_PER_DEG = 111_000; // ~111 km per degree (same scale as the area model's 111.32/110.574)
|
||||
const TOL_DEG = TOLERANCE_M / M_PER_DEG; // @turf/simplify works in degree space → ≈ 0.00045°
|
||||
const R4 = 4; // coordinate precision (decimal places) — same as the other scripts
|
||||
|
||||
// --- rounding / normalization (same conventions as the other scripts) ----------
|
||||
const rN = (v, N) => Math.round(v * 10 ** N) / 10 ** N;
|
||||
function roundRing(ring, N = R4) {
|
||||
const out = [];
|
||||
for (const [x, y] of ring) {
|
||||
const p = [rN(x, N), rN(y, N)];
|
||||
const last = out[out.length - 1];
|
||||
if (!last || last[0] !== p[0] || last[1] !== p[1]) out.push(p);
|
||||
}
|
||||
if (out.length > 1 && out[0][0] === out[out.length - 1][0] && out[0][1] === out[out.length - 1][1]) out.pop();
|
||||
if (out.length < 3) return ring; // degenerate — keep verbatim, never corrupt a ring
|
||||
return [...out, [...out[0]]];
|
||||
}
|
||||
|
||||
// --- tiny geometry helpers -----------------------------------------------------
|
||||
const polysOf = (g) => (g.type === 'Polygon' ? [g.coordinates] : g.coordinates);
|
||||
const ringsOf = (g) => polysOf(g).flatMap((p) => p);
|
||||
const countVerts = (g) => ringsOf(g).reduce((s, r) => s + r.length, 0);
|
||||
const countParts = (g) => (g.type === 'Polygon' ? 1 : g.coordinates.length);
|
||||
const countRings = (g) => ringsOf(g).length;
|
||||
const countHoles = (g) => polysOf(g).reduce((s, p) => s + Math.max(0, p.length - 1), 0);
|
||||
|
||||
/**
|
||||
* Smooth one closed ring with a single @turf/simplify (Douglas–Peucker) pass.
|
||||
* Only removes vertices — never adds, never drops the ring. Degenerate rings
|
||||
* (<4 pts) are returned verbatim (simplify would throw); a ring DP would
|
||||
* over-collapse below a valid 4-pt ring is kept as-is; any error keeps the
|
||||
* original. Never throws.
|
||||
*/
|
||||
function smoothRing(ring) {
|
||||
if (!Array.isArray(ring) || ring.length < 4) return ring; // keep degenerate verbatim
|
||||
try {
|
||||
const feat = { type: 'Feature', geometry: { type: 'Polygon', coordinates: [ring] } };
|
||||
const next = simplify(feat, { tolerance: TOL_DEG }).geometry.coordinates[0];
|
||||
if (!Array.isArray(next) || next.length < 4) return ring; // over-collapsed — keep original
|
||||
const closed =
|
||||
next[next.length - 1][0] === next[0][0] && next[next.length - 1][1] === next[0][1]
|
||||
? next
|
||||
: [...next, [next[0][0], next[0][1]]];
|
||||
const rounded = roundRing(closed);
|
||||
return rounded.length >= 4 ? rounded : ring;
|
||||
} catch {
|
||||
return ring;
|
||||
}
|
||||
}
|
||||
|
||||
/** Smooth every ring of a geometry. Never drops a ring or a part. */
|
||||
function smoothGeom(geom) {
|
||||
const newPolys = polysOf(geom).map((poly) => poly.map(smoothRing));
|
||||
if (geom.type === 'Polygon' && newPolys.length === 1) return { type: 'Polygon', coordinates: newPolys[0] };
|
||||
return { type: 'MultiPolygon', coordinates: newPolys };
|
||||
}
|
||||
|
||||
// --- main ----------------------------------------------------------------------
|
||||
function main() {
|
||||
const t0 = Date.now();
|
||||
const rawIn = readFileSync(SRC);
|
||||
const fc = JSON.parse(rawIn);
|
||||
const inBytes = Buffer.byteLength(rawIn);
|
||||
console.log(`input: ${fc.features.length} regions (${(inBytes / 1024).toFixed(0)} KB) from ${SRC}`);
|
||||
console.log(`mode: Douglas–Peucker via @turf/simplify, tolerance ${TOLERANCE_M} m (≈ ${TOL_DEG}°)`);
|
||||
|
||||
// before stats
|
||||
let vb = 0, hb = 0, pb = 0, rb = 0, degenerate = 0;
|
||||
for (const f of fc.features) {
|
||||
vb += countVerts(f.geometry);
|
||||
hb += countHoles(f.geometry);
|
||||
pb += countParts(f.geometry);
|
||||
rb += countRings(f.geometry);
|
||||
for (const r of ringsOf(f.geometry)) if (r.length < 4) degenerate++;
|
||||
}
|
||||
|
||||
const outFeatures = fc.features.map((f) => {
|
||||
const g = smoothGeom(f.geometry);
|
||||
return { type: 'Feature', id: f.id, properties: { name: f.properties.name, parent: f.properties.parent }, geometry: g };
|
||||
});
|
||||
const out = { type: 'FeatureCollection', features: outFeatures };
|
||||
|
||||
// after stats + change count (compare against the original, in order)
|
||||
let va = 0, ha = 0, pa = 0, ra = 0, changed = 0;
|
||||
for (let i = 0; i < out.features.length; i++) {
|
||||
const f = out.features[i];
|
||||
va += countVerts(f.geometry);
|
||||
ha += countHoles(f.geometry);
|
||||
pa += countParts(f.geometry);
|
||||
ra += countRings(f.geometry);
|
||||
if (JSON.stringify(f.geometry) !== JSON.stringify(fc.features[i].geometry)) changed++;
|
||||
}
|
||||
const afterVerts = new Map(out.features.map((f) => [f.id, countVerts(f.geometry)]));
|
||||
|
||||
const json = JSON.stringify(out);
|
||||
writeFileSync(OUT, json + '\n');
|
||||
const outBytes = Buffer.byteLength(json) + 1;
|
||||
|
||||
console.log(`\n--- RESULTS ---`);
|
||||
console.log(`regions: ${fc.features.length} → ${out.features.length} (unchanged)`);
|
||||
console.log(`vertices (incl. ring closure): ${vb} → ${va} removed ${vb - va} (${(100 * (vb - va) / vb).toFixed(2)}%)`);
|
||||
console.log(`rings: ${rb} → ${ra} parts: ${pb} → ${pa} holes: ${hb} → ${ha} (all unchanged)`);
|
||||
console.log(`regions whose geometry changed: ${changed} / ${fc.features.length}`);
|
||||
console.log(`degenerate rings (<4 pts, kept verbatim): ${degenerate}`);
|
||||
console.log(`file: ${(inBytes / 1024).toFixed(0)} KB → ${(outBytes / 1024).toFixed(0)} KB (${(outBytes / 1024 / 1024).toFixed(2)} MB)`);
|
||||
|
||||
// Diagnose the "messy" regions: the real problem is fragmentation — the
|
||||
// dissolve left coherent regions as many disconnected parts. Rank by part
|
||||
// count (then total vertices) so these surface; Kocelje/Kavadartsi are here.
|
||||
const messy = fc.features
|
||||
.map((f) => ({
|
||||
id: f.id,
|
||||
name: f.properties.name,
|
||||
parent: f.properties.parent,
|
||||
parts: countParts(f.geometry),
|
||||
vb: countVerts(f.geometry),
|
||||
}))
|
||||
.sort((a, b) => b.parts - a.parts || b.vb - a.vb)
|
||||
.slice(0, 15);
|
||||
console.log(`\nMOST-MESSY (top ${messy.length} by fragmentation = parts, then vertices):`);
|
||||
console.log(` id name country parts verts verts(after)`);
|
||||
for (const m of messy)
|
||||
console.log(` ${m.id.padEnd(10)} ${m.name.slice(0, 37).padEnd(38)} ${m.parent.padEnd(7)} ${String(m.parts).padStart(4)} ${String(m.vb).padStart(5)} ${String(afterVerts.get(m.id)).padStart(5)}`);
|
||||
|
||||
console.log(`\nwrote ${OUT}; elapsed ${((Date.now() - t0) / 1000).toFixed(1)}s`);
|
||||
}
|
||||
|
||||
main();
|
||||
Reference in New Issue
Block a user