Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
 kamilkrzywda
|
e92bf47d7d | ||
|
kamilkrzywda
|
f1cc4fbc10 | ||
|
kamilkrzywda
|
97702940cd | ||
|
kamilkrzywda
|
8eedc37e05 | ||
|
kamilkrzywda
|
69782aad69 | ||
|
kamilkrzywda
|
7bf11fa5b9 |
@@ -2,6 +2,31 @@
|
||||
|
||||
All notable changes to **History** are listed here, newest first.
|
||||
|
||||
## v0.16.0 — 2026-10-13 09:37
|
||||
- **Smoothed the jagged sub-national region boundaries with Douglas–Peucker vertex-thinning (Part of #16).** The v0.14 coarsening (boolean dissolve) and Natural Earth's 1:10m digitization left some boundaries overly jagged — the worst being regions the dissolve split into many small zig-zag fragments, e.g. **SI-048 Kocevje (Slovenia, 57 parts)** and **MK-36 Kavadartsi (N. Macedonia, 8 parts)**. The new `scripts/smooth-regions.mjs` (`npm run smooth:regions`) runs `@turf/simplify` (Ramer–Douglas–Peucker, tolerance ~**50 m**) over **every ring of every polygon**, dropping the redundant "in-between" vertices of a shallow zig-zag while keeping the overall shape.
|
||||
- **Vertex-thinning only — no topology change.** DP only removes points: it never moves a border, never merges/dissolves a part, and never creates or removes a ring. So the dataset contract is fully preserved — still **1,796 regions** with identical `id` / `properties.name` / `properties.parent`, all **177 countries** covered, the same **5,026 parts / 5,027 rings**, the single **KZ-KZY** hole, and all **83 islands**. The 18 degenerate 3-point "micro-dot" rings (Ragged Island, the Paracels, …) are kept verbatim (`@turf/simplify` requires ≥4 pts and would otherwise throw).
|
||||
- **A gentle pass, reported honestly.** At 50 m the dataset is already fairly smooth (the v0.14 dissolve produced low-vertex, widely-spaced boundaries — median consecutive-vertex spacing ~18 km), so this is a light cleanup: **111,891 → 111,175 vertices (716 removed, 0.64%)** across **542 of 1,796** regions. **Kocelje 612 → 599** and **Kavadartsi 169 → 163** verts; both keep their exact part count (the "mess" there is fragmentation, which thinning — under the no-topology-change constraint — does not fix). The file shrinks **2,302,473 → 2,289,528 bytes (2.29 MB)**. Bump `TOLERANCE_M` to 100 / 200 m and re-run for a stronger pass (100 m → 974 removed; 200 m → 1,312 removed) — the pass stays idempotent either way.
|
||||
- **The "messy" regions are really fragmentation artifacts, not fine jaggedness.** Ranking by **part density** (parts packed per unit area) rather than raw part count — which is dominated by legitimate *dispersed* archipelagos (Nunavut 213, Alaska 159, Antarctica 135, British Columbia 84) — surfaces the genuinely messy **coherent regions the dissolve left fragmented**: **SI-048 Kocevje (SVN, 57 parts in ~16,600 km²)**, **GR-H Stereá Elláda / Central Greece (GRC, 53 parts)**, **KR-46 South Jeolla (KOR, 28 parts)**, **SE-C Uppsala (SWE, 19 parts)**, **HR-13 Zadarska (HRV, 17 parts)**, plus the milder Balkan **MK-36 Kavadartsi (MKD, 8 parts)**. These real land regions (the Balkan ones in particular) ended up as many scattered fragments — the "similar shape problems".
|
||||
- **Deterministic + idempotent.** One `@turf/simplify` pass at a fixed tolerance, then 4-dp rounding (the same convention as the other scripts). The output already sits at the pass's fixed point, so re-running on the smoothed file is byte-identical (sha256 `70a43541…`, verified across repeated runs); `public/regions.geo.json` and the built `dist/regions.geo.json` are sha256-identical.
|
||||
- **Tests.** `scripts/regions.test.ts` gains an eighth test pinning the v0.16 fixed point: 1,796 regions, 5,026 parts, 5,027 rings, the single KZ-KZY hole, and exactly **111,175** vertices (8 tests total). All prior assertions (well-formed, unique ids, 177-country coverage, area floor, holes, coverage band) pass unchanged on the smoothed dataset.
|
||||
- Part of #16
|
||||
|
||||
## v0.15.0 — 2026-10-12 13:49
|
||||
- **Filled the small holes left by the v0.14 coarsening (Part of #16).** The coarsened `public/regions.geo.json` still carried **2,245 tiny enclosed holes** (all < 500 km² in practice) — unfilled patches left by the boolean dissolves and Natural Earth's own digitization, which showed up as "holes in regions". The new `scripts/cleanup-regions.mjs` (`npm run cleanup:regions`) drops every inner ring smaller than the 1,000 km² threshold so each region becomes solid: across **498 features, 56,484 km²** of artifact area was filled, removing the visible unfilled dots.
|
||||
- **Real water is kept, not erased.** Any enclosed hole ≥ 1,000 km² survives as a hole. In this dataset the genuinely large lakes (the Great Lakes, the Caspian, the Aral, Lake Superior) had already been dissolved by the v0.14 coarsening, so none remain to preserve; the only surviving hole is a single medium one — **KZ-KZY (Kyzylorda, Kazakhstan) at 5,858 km²**, a real water body in the Aral basin — which is kept. The 1,000 km² threshold sits comfortably between the tiny artifacts (all < 500) and any genuine lake, so it fills exactly the artifacts and nothing else.
|
||||
- **The dataset contract is untouched.** Still **1,796 regions** with identical `id`s / `properties.name` / `properties.parent` (0 mismatches), all **177 countries** still covered, the ~100 km floor and the island exemption intact — only inner rings were dropped, never a feature or its identity. The file shrinks 2,431 → **2,249 KB (2.20 MB)** (fewer inner rings).
|
||||
- **Deterministic + idempotent.** Fixed threshold, deterministic planar geometry, 4-dp rounding; re-running on the cleaned file rewrites a byte-identical file (sha256-verified). Bridging very-close MultiPolygon parts is available behind an opt-in `--bridge` flag but is **off by default**, because the union it performs can itself mint new medium-sized holes — counter to the fill-holes goal — so the shipped run is the clean hole-fill only.
|
||||
- **Tests.** `scripts/regions.test.ts` gains a seventh test asserting that no enclosed hole below the cleanup threshold remains and that only a handful of real water bodies survive (57 tests total). `public/regions.geo.json` and the built `dist/regions.geo.json` are sha256-identical.
|
||||
- Part of #16.
|
||||
|
||||
## v0.14.0 — 2026-10-12 09:51
|
||||
- **Coarsened the sub-national choropleth dataset to a ~100 km floor (Part of #16).** `public/regions.geo.json` shrinks from 4,138 real administrative regions to **1,796** (2,342 merges): every region smaller than ~100×100 km (10,000 km²) that has a same-country neighbor within 0.2° (≈22 km) of its bounding box is **dissolved into its nearest such neighbor** (nearest by centroid distance; ties → larger area, then id). Standalone cities and micro-districts collapse into the region around them: `US-DC` (191 km²) into Maryland, `FR-75` Paris (59 km²) into Hauts-de-Seine, the UK's 232 admin-1 districts down to **16** regions, and all of North Macedonia's 85 municipalities into one whole-country region.
|
||||
- **Islands are exempt.** A region with no same-country neighbor within 0.2° keeps its shape whatever its size — **83** such small islands survive in the final set (Corsica, the Kerguelen/Crozet archipelagos, the Bahamas districts, Lord Howe, …) and the coarsening's fixed point leaves **0** non-island regions below the floor.
|
||||
- **Real dissolve, not overlap.** Each merge is a real boolean union (`@turf/union`, polygon clipping) that removes the shared boundary between the merged region and its host, yielding one clean polygon — the final dataset has **0** fallback (non-dissolved) unions. Passes iterate smallest-area-first to a fixed point (2 passes on the v0.13 data, ~7 s); the output is sorted by (parent, id) at 4-dp precision and is byte-reproducible: re-running on the coarsened file reaches the fixed point immediately and rewrites an identical file (sha256-verified).
|
||||
- **Numbers.** Per-country region count: min 1 / median 7 / max 80 (Russia; was 1 / 15 / 232 — the UK). Region areas: median 23,933 km²; smallest ≈0 (degenerate micro-dots like Ragged Island and the Paracel Islands, kept as islands); largest is Antarctica itself (≈21.8M km² in the planar model, exempt — it wraps a full 360°). 158 of the 177 countries had at least one merge. The file is 2,431 KB (2.37 MB) — under the 5 MB guard, so no Douglas–Peucker pass was needed.
|
||||
- **Tooling + tests.** New `scripts/coarsen-regions.mjs` (`npm run coarsen:regions`) performs the merge in place; `scripts/regions.test.ts` gains a sixth test asserting that below-floor non-island regions stay under 1% of the dataset (currently 0) alongside the existing well-formed / unique-id / 177-country coverage / area / coverage-band checks (56 tests total). The map's data contract is unchanged (`properties.parent` → RegionMap), so `WorldMap.tsx`, `App.tsx`, `shared/protocol.ts`, and `server/map.ts` all keep working as-is.
|
||||
- Part of #16.
|
||||
|
||||
## v0.13.0 — 2026-10-12 08:30
|
||||
- **Replaced the geometric sub-region grid with real named sub-national administrative regions (#16, PR 2).** The choropleth source `public/regions.geo.json` now contains real named administrative regions — states, provinces, governorates, oblasts, … (Natural Earth admin-1, 1:10m) — instead of the abstract ~100–200 km geometric grid. Each region keeps a stable `id` and a `name`. The map's data contract is **unchanged** (`properties.parent` → the parent country's ISO_A3, `properties.name` → the region name), so no change to the map code or the LLM contract: `WorldMap.tsx`, `App.tsx`, `shared/protocol.ts`, and `server/map.ts` all keep working as-is.
|
||||
- **Generator rewritten** — `scripts/generate-regions.mjs` (same path, dependency-free, `npm run generate:regions`) now groups the admin-1 features by their `adm0_a3` (the parent's ISO_A3), keeps only parents in the 177-country set, and id's each region with its ISO 3166-2 code when present (e.g. `US-CA`, `FR-75`, `RU-MOW`) else `<ISO_A3>-<nn>`; within a country, ids are disambiguated with a `-2/-3/…` suffix on collision (ISO 3166-2 codes are not always unique within a country — e.g. all nine of Bosnia's entities report `BA-BIH`). A country with no admin-1 data would collapse to one whole-country region `<ISO_A3>-01` (0 are needed at 1:10m, which covers all 177). Coordinates are rounded to 4 decimal places, and the file is Douglas–Peucker-simplified only if it exceeds the ~8 MB guard. Output is sorted by (parent, id) and fully deterministic.
|
||||
|
||||
Generated
+159
-2
@@ -1,12 +1,12 @@
|
||||
{
|
||||
"name": "history",
|
||||
"version": "0.1.0",
|
||||
"version": "0.16.0",
|
||||
"lockfileVersion": 3,
|
||||
"requires": true,
|
||||
"packages": {
|
||||
"": {
|
||||
"name": "history",
|
||||
"version": "0.1.0",
|
||||
"version": "0.16.0",
|
||||
"dependencies": {
|
||||
"@radix-ui/react-dialog": "^1.1.6",
|
||||
"@radix-ui/react-label": "^2.1.2",
|
||||
@@ -32,6 +32,8 @@
|
||||
"@eslint/js": "^9.20.0",
|
||||
"@playwright/test": "^1.62.1",
|
||||
"@tailwindcss/vite": "^4.1.4",
|
||||
"@turf/simplify": "^7.4.0",
|
||||
"@turf/union": "^7.4.0",
|
||||
"@types/better-sqlite3": "^7.6.13",
|
||||
"@types/express": "^4.17.25",
|
||||
"@types/node": "^22.13.0",
|
||||
@@ -3334,6 +3336,133 @@
|
||||
"vite": "^5.2.0 || ^6 || ^7 || ^8"
|
||||
}
|
||||
},
|
||||
"node_modules/@turf/boolean-point-on-line": {
|
||||
"version": "7.4.0",
|
||||
"resolved": "https://registry.npmjs.org/@turf/boolean-point-on-line/-/boolean-point-on-line-7.4.0.tgz",
|
||||
"integrity": "sha512-5i5UBeZf/LuzgavkIj8L8L5/8SYWItWzQQcE9ymFZr60lV5lM8eFvQDfzAz2R3WQFCrxXExPqNvAVZOKGUyvoA==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@turf/helpers": "7.4.0",
|
||||
"@turf/invariant": "7.4.0",
|
||||
"@types/geojson": "^7946.0.10",
|
||||
"tslib": "^2.8.1"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://opencollective.com/turf"
|
||||
}
|
||||
},
|
||||
"node_modules/@turf/clean-coords": {
|
||||
"version": "7.4.0",
|
||||
"resolved": "https://registry.npmjs.org/@turf/clean-coords/-/clean-coords-7.4.0.tgz",
|
||||
"integrity": "sha512-xl3lVPey/FyVc3Z+drAWtVuVtvt737RHKGUMGyuskmKYW0JUeFDgqSR0OnrDfxXWb58Im/65BgPd1B+TUA9WfA==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@turf/boolean-point-on-line": "7.4.0",
|
||||
"@turf/helpers": "7.4.0",
|
||||
"@turf/invariant": "7.4.0",
|
||||
"@types/geojson": "^7946.0.10",
|
||||
"tslib": "^2.8.1"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://opencollective.com/turf"
|
||||
}
|
||||
},
|
||||
"node_modules/@turf/clone": {
|
||||
"version": "7.4.0",
|
||||
"resolved": "https://registry.npmjs.org/@turf/clone/-/clone-7.4.0.tgz",
|
||||
"integrity": "sha512-IfYnuil7XYJauy3crzIYEr26QkmBiTgFdGfYwUUe3S6dawX+lyb3vhuaYyssEPcCJq83g0G7hwxZy7141Mmzjg==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@turf/helpers": "7.4.0",
|
||||
"@types/geojson": "^7946.0.10",
|
||||
"tslib": "^2.8.1"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://opencollective.com/turf"
|
||||
}
|
||||
},
|
||||
"node_modules/@turf/helpers": {
|
||||
"version": "7.4.0",
|
||||
"resolved": "https://registry.npmjs.org/@turf/helpers/-/helpers-7.4.0.tgz",
|
||||
"integrity": "sha512-7PAwLZqOdRzTI5g9bHvUwlloAXPDH/mlajtryk0tw4ZwGMtmXsAyF4QundsAMfy4u48Fyd3AUqMXY0SMxqJGWg==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@types/geojson": "^7946.0.10",
|
||||
"tslib": "^2.8.1"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://opencollective.com/turf"
|
||||
}
|
||||
},
|
||||
"node_modules/@turf/invariant": {
|
||||
"version": "7.4.0",
|
||||
"resolved": "https://registry.npmjs.org/@turf/invariant/-/invariant-7.4.0.tgz",
|
||||
"integrity": "sha512-OAsc3qdNx+tRqzWmMNFMnVlWWACIqnYqIejZKvb2oKkKPYJJrURPXZ6OdrGD58ljJMolLoqwIZGSx3VndaEjxg==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@turf/helpers": "7.4.0",
|
||||
"@types/geojson": "^7946.0.10",
|
||||
"tslib": "^2.8.1"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://opencollective.com/turf"
|
||||
}
|
||||
},
|
||||
"node_modules/@turf/meta": {
|
||||
"version": "7.4.0",
|
||||
"resolved": "https://registry.npmjs.org/@turf/meta/-/meta-7.4.0.tgz",
|
||||
"integrity": "sha512-3cLUvlEyDuSnMSzrjhaLAEiYR8xhbfWyTVQlrlEw40xL81d4KF4PqUWbjTXKpXZStdYbet2GCurl79KMypNw6g==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@turf/helpers": "7.4.0",
|
||||
"@types/geojson": "^7946.0.10",
|
||||
"tslib": "^2.8.1"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://opencollective.com/turf"
|
||||
}
|
||||
},
|
||||
"node_modules/@turf/simplify": {
|
||||
"version": "7.4.0",
|
||||
"resolved": "https://registry.npmjs.org/@turf/simplify/-/simplify-7.4.0.tgz",
|
||||
"integrity": "sha512-HTolHFuXLReKHJoh3iz92+WpF5EsuCmmZR7fNv3hWnA4hZfkuEzbGB/WZqRdQpvDs99IUS8QIc6BAp6FHzQbBQ==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@turf/clean-coords": "7.4.0",
|
||||
"@turf/clone": "7.4.0",
|
||||
"@turf/helpers": "7.4.0",
|
||||
"@turf/meta": "7.4.0",
|
||||
"@types/geojson": "^7946.0.10",
|
||||
"tslib": "^2.8.1"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://opencollective.com/turf"
|
||||
}
|
||||
},
|
||||
"node_modules/@turf/union": {
|
||||
"version": "7.4.0",
|
||||
"resolved": "https://registry.npmjs.org/@turf/union/-/union-7.4.0.tgz",
|
||||
"integrity": "sha512-SYVtsCW9IznTyKlcGWxssRrf90p/hdpch1UeIcZc31pkSVdmeLOyuzPx0ef3UPmaF//fgXAphMph6JWA/FpKbA==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@turf/helpers": "7.4.0",
|
||||
"@turf/meta": "7.4.0",
|
||||
"@types/geojson": "^7946.0.10",
|
||||
"polyclip-ts": "^0.16.8",
|
||||
"tslib": "^2.8.1"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://opencollective.com/turf"
|
||||
}
|
||||
},
|
||||
"node_modules/@types/babel__core": {
|
||||
"version": "7.20.5",
|
||||
"resolved": "https://registry.npmjs.org/@types/babel__core/-/babel__core-7.20.5.tgz",
|
||||
@@ -4177,6 +4306,16 @@
|
||||
"require-from-string": "^2.0.2"
|
||||
}
|
||||
},
|
||||
"node_modules/bignumber.js": {
|
||||
"version": "9.3.1",
|
||||
"resolved": "https://registry.npmjs.org/bignumber.js/-/bignumber.js-9.3.1.tgz",
|
||||
"integrity": "sha512-Ko0uX15oIUS7wJ3Rb30Fs6SkVbLmPBAKdlm7q9+ak9bbIeFf0MwuBsQV6z7+X768/cHsfg+WlysDWJcmthjsjQ==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": "*"
|
||||
}
|
||||
},
|
||||
"node_modules/bindings": {
|
||||
"version": "1.5.0",
|
||||
"resolved": "https://registry.npmjs.org/bindings/-/bindings-1.5.0.tgz",
|
||||
@@ -6695,6 +6834,17 @@
|
||||
"node": ">=20"
|
||||
}
|
||||
},
|
||||
"node_modules/polyclip-ts": {
|
||||
"version": "0.16.8",
|
||||
"resolved": "https://registry.npmjs.org/polyclip-ts/-/polyclip-ts-0.16.8.tgz",
|
||||
"integrity": "sha512-JPtKbDRuPEuAjuTdhR62Gph7Is2BS1Szx69CFOO3g71lpJDFo78k4tFyi+qFOMVPePEzdSKkpGU3NBXPHHjvKQ==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"bignumber.js": "^9.1.0",
|
||||
"splaytree-ts": "^1.0.2"
|
||||
}
|
||||
},
|
||||
"node_modules/postcss": {
|
||||
"version": "8.5.29",
|
||||
"resolved": "https://registry.npmjs.org/postcss/-/postcss-8.5.29.tgz",
|
||||
@@ -7514,6 +7664,13 @@
|
||||
"node": ">=0.10.0"
|
||||
}
|
||||
},
|
||||
"node_modules/splaytree-ts": {
|
||||
"version": "1.0.2",
|
||||
"resolved": "https://registry.npmjs.org/splaytree-ts/-/splaytree-ts-1.0.2.tgz",
|
||||
"integrity": "sha512-0kGecIZNIReCSiznK3uheYB8sbstLjCZLiwcQwbmLhgHJj2gz6OnSPkVzJQCMnmEz1BQ4gPK59ylhBoEWOhGNA==",
|
||||
"dev": true,
|
||||
"license": "BDS-3-Clause"
|
||||
},
|
||||
"node_modules/stackback": {
|
||||
"version": "0.0.2",
|
||||
"resolved": "https://registry.npmjs.org/stackback/-/stackback-0.0.2.tgz",
|
||||
|
||||
+6
-1
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "history",
|
||||
"version": "0.13.0",
|
||||
"version": "0.16.0",
|
||||
"private": true,
|
||||
"type": "module",
|
||||
"description": "AI-driven alternate-history simulator — the LLM is the world engine (Pax Historia style).",
|
||||
@@ -10,6 +10,9 @@
|
||||
"start": "node server/dist/index.js",
|
||||
"test": "vitest run",
|
||||
"generate:regions": "node scripts/generate-regions.mjs",
|
||||
"coarsen:regions": "node scripts/coarsen-regions.mjs",
|
||||
"cleanup:regions": "node scripts/cleanup-regions.mjs",
|
||||
"smooth:regions": "node scripts/smooth-regions.mjs",
|
||||
"typecheck": "tsc --noEmit",
|
||||
"lint": "eslint .",
|
||||
"e2e": "playwright test"
|
||||
@@ -39,6 +42,8 @@
|
||||
"@eslint/js": "^9.20.0",
|
||||
"@playwright/test": "^1.62.1",
|
||||
"@tailwindcss/vite": "^4.1.4",
|
||||
"@turf/simplify": "^7.4.0",
|
||||
"@turf/union": "^7.4.0",
|
||||
"@types/better-sqlite3": "^7.6.13",
|
||||
"@types/express": "^4.17.25",
|
||||
"@types/node": "^22.13.0",
|
||||
|
||||
File diff suppressed because one or more lines are too long
@@ -0,0 +1,323 @@
|
||||
#!/usr/bin/env node
|
||||
/**
|
||||
* scripts/cleanup-regions.mjs — removes the small holes left by coarsening.
|
||||
*
|
||||
* Run: npm run cleanup:regions (in place on public/regions.geo.json)
|
||||
* node scripts/cleanup-regions.mjs [out] [src] [--bridge]
|
||||
*
|
||||
* The v0.14 coarsening produced a clean 1,796-region dataset, but small
|
||||
* unfilled patches ("holes") remain inside regions — artifacts of the boolean
|
||||
* dissolves and Natural Earth's own digitization. This fixes that in place,
|
||||
* WITHOUT touching the dataset's contract (the region count, the `id`s, the
|
||||
* `properties = { name, parent }`, the ~100 km floor and the island exemption
|
||||
* are all preserved — only inner rings are dropped).
|
||||
*
|
||||
* ENCLOSED HOLES — every hole (inner ring) whose area is < HOLE_AREA_MAX_KM2
|
||||
* is dropped, so the region fills in to be solid. Any larger hole (a genuine
|
||||
* water body) is kept. NOTE: the big real lakes (Great Lakes, Caspian, Aral,
|
||||
* Lake Superior, …) were already dissolved by the v0.14 coarsening, so they
|
||||
* are not present as holes here; the only hole above the threshold in this
|
||||
* dataset is a single medium one (~5,858 km2, kept). A 1,000 km2 threshold
|
||||
* is comfortably above the 2,252 tiny artifact holes (all < 500 km2) and
|
||||
* comfortably below any large real lake, so it fills exactly the artifacts.
|
||||
*
|
||||
* BRIDGING (opt-in, `--bridge`) — a MultiPolygon whose separate parts sit
|
||||
* only a short distance apart (a thin gap across a strait, a nearby island)
|
||||
* leaves a visible crack of background. This joins each such close pair with
|
||||
* a small connector polygon and a boolean union, closing the crack while
|
||||
* genuinely far parts (islands, separated territories) stay separate. It is
|
||||
* OFF by default: the union itself can mint new (medium) holes, which is
|
||||
* counter to the primary "fill holes" goal, so the default run is the
|
||||
* clean, deterministic hole-fill only.
|
||||
*
|
||||
* Deterministic + idempotent: fixed threshold, deterministic planar geometry,
|
||||
* 4-dp rounding. Re-running on an already-clean file rewrites the same file
|
||||
* (no small holes remain to fill; the kept holes are above the threshold).
|
||||
*/
|
||||
|
||||
import { readFileSync, writeFileSync } from 'node:fs';
|
||||
import path from 'node:path';
|
||||
import { fileURLToPath } from 'node:url';
|
||||
import { union } from '@turf/union';
|
||||
import { featureCollection } from '@turf/helpers';
|
||||
|
||||
const here = path.dirname(fileURLToPath(import.meta.url));
|
||||
const root = path.resolve(here, '..');
|
||||
const DEFAULT_FILE = path.join(root, 'public', 'regions.geo.json');
|
||||
// positional args (out, src) plus named flags; keep the two orthogonal
|
||||
const args = process.argv.slice(2).filter((a) => !a.startsWith('-'));
|
||||
const flags = process.argv.slice(2).filter((a) => a.startsWith('-'));
|
||||
const BRIDGE = flags.includes('--bridge');
|
||||
const OUT = args[0] ? path.resolve(args[0]) : DEFAULT_FILE;
|
||||
const SRC = args[1] ? path.resolve(args[1]) : DEFAULT_FILE;
|
||||
|
||||
// --- parameters ---------------------------------------------------------------
|
||||
const HOLE_AREA_MAX_KM2 = 1000; // fill enclosed holes smaller than this (keep real lakes)
|
||||
const BRIDGE_MAX_KM = 30; // bridge part-gaps smaller than this …
|
||||
const BRIDGE_MIN_KM = 0.3; // … but only real gaps (a pair in (BRIDGE_MIN, BRIDGE_MAX))
|
||||
const BRIDGE_EXT_KM = 2; // extend each bridge end into its part (ensures union overlap)
|
||||
const BRIDGE_HW_MIN_KM = 2; // minimum half-width of a connector
|
||||
const BRIDGE_HW_MAX_KM = 20; // cap so a connector never becomes a big blob
|
||||
const R4 = 4; // coordinate precision (decimal places)
|
||||
const SLIVER_EPS_KM2 = 1e-6; // drop only truly-degenerate (≈zero-area) parts
|
||||
|
||||
// --- area model (identical to coarsen-regions.mjs / regions.test.ts) -----------
|
||||
const KM_LON = 111.32;
|
||||
const KM_LAT = 110.574;
|
||||
const rad = (deg) => (deg * Math.PI) / 180;
|
||||
function ringAreaKm2(ring) {
|
||||
let lat = 0;
|
||||
for (const [, la] of ring) lat += la;
|
||||
const kx = KM_LON * Math.cos(rad(ring.length ? lat / ring.length : 0));
|
||||
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 geomAreaKm2(geom) {
|
||||
if (!geom) return 0;
|
||||
const polys = geom.type === 'Polygon' ? [geom.coordinates] : geom.coordinates;
|
||||
let total = 0;
|
||||
for (const poly of polys) total += ringAreaKm2(poly[0]);
|
||||
return total;
|
||||
}
|
||||
|
||||
// --- rounding / normalization (same conventions as coarsen-regions.mjs) --------
|
||||
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 out;
|
||||
return [...out, [...out[0]]];
|
||||
}
|
||||
function roundAll(geom) {
|
||||
if (!geom || (geom.type !== 'Polygon' && geom.type !== 'MultiPolygon')) return null;
|
||||
const polys = (geom.type === 'Polygon' ? [geom.coordinates] : geom.coordinates)
|
||||
.map((poly) => poly.map((ring) => roundRing(ring)))
|
||||
.filter((poly) => poly.length >= 1 && poly.every((r) => r.length >= 3));
|
||||
if (!polys.length) return null;
|
||||
if (polys.length === 1 && geom.type === 'Polygon') return { type: 'Polygon', coordinates: polys[0] };
|
||||
return { type: 'MultiPolygon', coordinates: polys };
|
||||
}
|
||||
function normalizeGeom(geom) {
|
||||
const rounded = roundAll(geom);
|
||||
if (!rounded) return null;
|
||||
const all = rounded.type === 'Polygon' ? [rounded.coordinates] : rounded.coordinates;
|
||||
const kept = all.filter((poly) => ringAreaKm2(poly[0]) >= SLIVER_EPS_KM2);
|
||||
const polys = kept.length ? kept : all;
|
||||
if (polys.length === 1 && rounded.type === 'Polygon') return { type: 'Polygon', coordinates: polys[0] };
|
||||
return { type: 'MultiPolygon', coordinates: polys };
|
||||
}
|
||||
|
||||
// --- closest-point measurement (decimated planar point↔segment, ~km) ----------
|
||||
function toXY(ring) {
|
||||
let lat = 0;
|
||||
for (const [, la] of ring) lat += la;
|
||||
const kx = KM_LON * Math.cos(rad(ring.length ? lat / ring.length : 0));
|
||||
return ring.map(([lon, lat]) => [lon * kx, lat * KM_LAT]);
|
||||
}
|
||||
function dec(pts, maxN = 200) {
|
||||
if (pts.length <= maxN) return pts;
|
||||
const step = Math.ceil(pts.length / maxN);
|
||||
const out = [];
|
||||
for (let i = 0; i < pts.length; i += step) out.push(pts[i]);
|
||||
return out;
|
||||
}
|
||||
/**
|
||||
* Closest point-pair between two planar rings: returns { d, p, q } with p on A,
|
||||
* q on B and d = |p-q| in km (both on the decimated rings — a good-enough
|
||||
* approximation for bridging; a tiny offset is corrected by the extension).
|
||||
*/
|
||||
function ringClosest(AX, BX) {
|
||||
const A = dec(AX), B = dec(BX);
|
||||
let best = Infinity, bestP = null, bestQ = null;
|
||||
for (const p of A) {
|
||||
for (let i = 0; i < B.length - 1; i++) {
|
||||
const a = B[i], b = B[i + 1];
|
||||
const dx = b[0] - a[0], dy = b[1] - a[1];
|
||||
const l2 = dx * dx + dy * dy;
|
||||
let t = l2 === 0 ? 0 : ((p[0] - a[0]) * dx + (p[1] - a[1]) * dy) / l2;
|
||||
t = Math.max(0, Math.min(1, t));
|
||||
const c = [a[0] + t * dx, a[1] + t * dy];
|
||||
const dd = Math.hypot(p[0] - c[0], p[1] - c[1]);
|
||||
if (dd < best) { best = dd; bestP = p; bestQ = c; }
|
||||
}
|
||||
}
|
||||
for (const p of B) {
|
||||
for (let i = 0; i < A.length - 1; i++) {
|
||||
const a = A[i], b = A[i + 1];
|
||||
const dx = b[0] - a[0], dy = b[1] - a[1];
|
||||
const l2 = dx * dx + dy * dy;
|
||||
let t = l2 === 0 ? 0 : ((p[0] - a[0]) * dx + (p[1] - a[1]) * dy) / l2;
|
||||
t = Math.max(0, Math.min(1, t));
|
||||
const c = [a[0] + t * dx, a[1] + t * dy];
|
||||
const dd = Math.hypot(p[0] - c[0], p[1] - c[1]);
|
||||
if (dd < best) { best = dd; bestP = c; bestQ = p; }
|
||||
}
|
||||
}
|
||||
return { d: best, p: bestP, q: bestQ };
|
||||
}
|
||||
|
||||
/**
|
||||
* Build a thin connector (a quad in lon/lat) between two closest points p, q
|
||||
* (both in planar km). The connector is extended a little into each part so the
|
||||
* boolean union joins them, and its half-width is wide enough to span the local
|
||||
* gap (capped so it never becomes a big blob).
|
||||
*/
|
||||
function makeBridgeRing(p, q) {
|
||||
const gap = Math.hypot(q[0] - p[0], q[1] - p[1]);
|
||||
if (gap < 1e-3) return null; // coincident → nothing to bridge
|
||||
const midLat = (p[1] / KM_LAT + q[1] / KM_LAT) / 2;
|
||||
const kx = KM_LON * Math.cos(rad(midLat));
|
||||
const ux = (q[0] - p[0]) / gap, uy = (q[1] - p[1]) / gap; // unit p→q
|
||||
const nx = -uy, ny = ux; // perpendicular
|
||||
const hw = Math.min(BRIDGE_HW_MAX_KM, Math.max(BRIDGE_HW_MIN_KM, gap / 2));
|
||||
const ext = BRIDGE_EXT_KM;
|
||||
const pExt = [p[0] - ux * ext, p[1] - uy * ext];
|
||||
const qExt = [q[0] + ux * ext, q[1] + uy * ext];
|
||||
const toLL = ([x, y]) => [rN(x / kx, R4), rN(y / KM_LAT, R4)];
|
||||
const c1 = toLL([pExt[0] + nx * hw, pExt[1] + ny * hw]);
|
||||
const c2 = toLL([qExt[0] + nx * hw, qExt[1] + ny * hw]);
|
||||
const c3 = toLL([qExt[0] - nx * hw, qExt[1] - ny * hw]);
|
||||
const c4 = toLL([pExt[0] - nx * hw, pExt[1] - ny * hw]);
|
||||
return [c1, c2, c3, c4, c1];
|
||||
}
|
||||
|
||||
/** Bridge all close pairs of a MultiPolygon and union everything into one shape. */
|
||||
function bridgeParts(geom) {
|
||||
const parts = geom.coordinates;
|
||||
const partsXY = parts.map((p) => toXY(p[0]));
|
||||
const bridges = [];
|
||||
let bridgedPairs = 0;
|
||||
for (let i = 0; i < partsXY.length; i++) {
|
||||
for (let j = i + 1; j < partsXY.length; j++) {
|
||||
const { d, p, q } = ringClosest(partsXY[i], partsXY[j]);
|
||||
if (d > BRIDGE_MIN_KM && d < BRIDGE_MAX_KM) {
|
||||
const ring = makeBridgeRing(p, q);
|
||||
if (ring) { bridges.push(ring); bridgedPairs++; }
|
||||
}
|
||||
}
|
||||
}
|
||||
if (!bridges.length) return { geom, bridgedPairs: 0, changed: false };
|
||||
// union: original parts (as Polygons) + connector rings (as Polygons)
|
||||
const feats = parts.map((poly) => ({ type: 'Feature', geometry: { type: 'Polygon', coordinates: poly } }));
|
||||
for (const ring of bridges) feats.push({ type: 'Feature', geometry: { type: 'Polygon', coordinates: [ring] } });
|
||||
let u;
|
||||
try {
|
||||
u = union(featureCollection(feats));
|
||||
} catch (e) {
|
||||
console.error(` [warn] bridge union failed: ${e.message}`);
|
||||
return { geom, bridgedPairs: 0, changed: false };
|
||||
}
|
||||
const norm = u ? normalizeGeom(u.geometry) : null;
|
||||
// Guard: a good bridge only adds a little area. Reject the union if it lost
|
||||
// area (< 0.8×, a bad union that ate parts) or over-filled (> 1.3×, e.g. many
|
||||
// overlapping bridges in a dense archipelago) — keep the original instead.
|
||||
if (norm) {
|
||||
const na = geomAreaKm2(norm);
|
||||
const oa = geomAreaKm2(geom);
|
||||
if (oa > 0 && (na < 0.8 * oa || na > 1.3 * oa)) {
|
||||
return { geom, bridgedPairs: 0, changed: false };
|
||||
}
|
||||
}
|
||||
return { geom: norm ?? geom, bridgedPairs, changed: true, bridgedParts: u ? (u.geometry.type === 'Polygon' ? 1 : u.geometry.coordinates.length) : parts.length };
|
||||
}
|
||||
|
||||
// --- main ----------------------------------------------------------------------
|
||||
function main() {
|
||||
const t0 = Date.now();
|
||||
const fc = JSON.parse(readFileSync(SRC, 'utf8'));
|
||||
const inKB = (Buffer.byteLength(readFileSync(SRC)) / 1024).toFixed(0);
|
||||
console.log(`input: ${fc.features.length} regions (${inKB} KB) from ${SRC}`);
|
||||
console.log(`mode: holes <${HOLE_AREA_MAX_KM2} km2 filled, larger kept${BRIDGE ? `; + bridging part-gaps in (${BRIDGE_MIN_KM}, ${BRIDGE_MAX_KM}) km` : ''}`);
|
||||
|
||||
// diagnostics
|
||||
let holesFilled = 0, holesFilledArea = 0, holesKept = 0, holesKeptArea = 0, featuresTouchedHole = 0;
|
||||
let bridgedFeatures = 0, bridgedPairs = 0, partsBefore = 0, partsAfter = 0, areaBefore = 0, areaAfter = 0;
|
||||
const bridgeSamples = [];
|
||||
const keptHoleSamples = [];
|
||||
|
||||
const outFeatures = [];
|
||||
for (const f of fc.features) {
|
||||
let geom = f.geometry;
|
||||
|
||||
// ---- Opt-in: bridge close parts (additive connector + union) ----
|
||||
if (BRIDGE && geom.type === 'MultiPolygon' && geom.coordinates.length >= 2) {
|
||||
const before = { parts: geom.coordinates.length, area: geomAreaKm2(geom) };
|
||||
const res = bridgeParts(geom);
|
||||
if (res.changed) {
|
||||
geom = res.geom;
|
||||
bridgedFeatures++;
|
||||
bridgedPairs += res.bridgedPairs;
|
||||
partsBefore += before.parts;
|
||||
partsAfter += geom.type === 'Polygon' ? 1 : geom.coordinates.length;
|
||||
areaBefore += before.area;
|
||||
areaAfter += geomAreaKm2(geom);
|
||||
if (bridgeSamples.length < 20)
|
||||
bridgeSamples.push(`${f.id} ${f.properties.name} (${f.properties.parent}): ${before.parts}p→${geom.type === 'Polygon' ? 1 : geom.coordinates.length}p, ${res.bridgedPairs} bridge(s), ${Math.round(before.area)}→${Math.round(geomAreaKm2(geom))} km2`);
|
||||
}
|
||||
}
|
||||
|
||||
// ---- Fill small enclosed holes: drop inner rings < threshold, keep larger ----
|
||||
const isMulti = geom.type === 'MultiPolygon';
|
||||
const polys = isMulti ? geom.coordinates : [geom.coordinates];
|
||||
let touchedHole = false;
|
||||
const newPolys = polys.map((poly) => {
|
||||
const kept = [poly[0]]; // outer ring always kept
|
||||
for (let i = 1; i < poly.length; i++) {
|
||||
const area = ringAreaKm2(poly[i]);
|
||||
if (area < 1e-6) continue; // degenerate — drop
|
||||
if (area < HOLE_AREA_MAX_KM2) {
|
||||
holesFilled++; holesFilledArea += area; touchedHole = true; // fill (drop)
|
||||
} else {
|
||||
holesKept++; holesKeptArea += area;
|
||||
kept.push(poly[i]); // a genuine water body — keep the hole
|
||||
if (keptHoleSamples.length < 20) keptHoleSamples.push(`${f.id}(${f.properties.parent}) ${Math.round(area)} km2`);
|
||||
}
|
||||
}
|
||||
return kept;
|
||||
});
|
||||
if (touchedHole) featuresTouchedHole++;
|
||||
|
||||
const rebuilt = isMulti
|
||||
? { type: 'MultiPolygon', coordinates: newPolys }
|
||||
: { type: 'Polygon', coordinates: newPolys[0] };
|
||||
// normalize (round 4dp, drop degenerate). NEVER drop a feature: if nothing
|
||||
// usable survives (a degenerate 3-pt 0-area micro-dot), keep the
|
||||
// hole-filled (rebuilt) geometry, else the untouched original.
|
||||
const norm = normalizeGeom(rebuilt);
|
||||
outFeatures.push({ type: 'Feature', id: f.id, properties: { name: f.properties.name, parent: f.properties.parent }, geometry: norm ?? rebuilt ?? geom });
|
||||
}
|
||||
|
||||
const out = { type: 'FeatureCollection', features: outFeatures };
|
||||
const json = JSON.stringify(out);
|
||||
const outKB = (Buffer.byteLength(json) / 1024).toFixed(0);
|
||||
writeFileSync(OUT, json + '\n');
|
||||
|
||||
console.log(`\n--- RESULTS ---`);
|
||||
console.log(`regions: ${fc.features.length} → ${out.features.length} (should be unchanged)`);
|
||||
console.log(`file: ${inKB} KB → ${outKB} KB (${(outKB / 1024).toFixed(2)} MB)`);
|
||||
console.log(`\nENCLOSED HOLES:`);
|
||||
console.log(` filled ${holesFilled} holes (${Math.round(holesFilledArea).toLocaleString('en-US')} km2) in ${featuresTouchedHole} features`);
|
||||
console.log(` kept ${holesKept} hole(s) (${Math.round(holesKeptArea).toLocaleString('en-US')} km2) as real water`);
|
||||
if (keptHoleSamples.length) console.log(` kept-hole list: ${keptHoleSamples.join(', ')}`);
|
||||
if (BRIDGE) {
|
||||
console.log(`\nBRIDGING (part-gaps):`);
|
||||
console.log(` bridged ${bridgedFeatures} features (${bridgedPairs} close pairs): parts ${partsBefore} → ${partsAfter}, area ${Math.round(areaBefore).toLocaleString('en-US')} → ${Math.round(areaAfter).toLocaleString('en-US')} km2`);
|
||||
for (const s of bridgeSamples) console.log(` ${s}`);
|
||||
} else {
|
||||
console.log(`\nbridging: skipped (pass --bridge to enable)`);
|
||||
}
|
||||
console.log(`\nwrote ${OUT}; elapsed ${((Date.now() - t0) / 1000).toFixed(1)}s`);
|
||||
}
|
||||
|
||||
main();
|
||||
@@ -0,0 +1,612 @@
|
||||
#!/usr/bin/env node
|
||||
/**
|
||||
* scripts/coarsen-regions.mjs — coarsens the committed `public/regions.geo.json`
|
||||
* in place, so the map is genuinely coarser, not just finer-grained.
|
||||
*
|
||||
* Rule (per user request: "focus on joining cities to the region around it.
|
||||
* Regions shouldn't be smaller than around 100x100km, excluding islands"):
|
||||
*
|
||||
* FLOOR — no region should be smaller than ~100×100 km = 10,000 km²,
|
||||
* EXCEPT islands.
|
||||
* ISLAND — a region is an island if it has NO same-country neighbor: no
|
||||
* other region with the same `properties.parent` whose bounding box
|
||||
* is within CLOSE_DEG (≈≤22 km) of its own. Small islands stay
|
||||
* as-is regardless of size (Corsica, the Hawaiian counties,
|
||||
* Okinawa, the Faroes, island micro-states, …).
|
||||
* MERGE — a region that is small (area < FLOOR) AND not an island is
|
||||
* merged into its NEAREST same-country neighbor (nearest by
|
||||
* centroid distance; tie-break → larger area, then lexicographic
|
||||
* id). Standalone cities (FR-75 Paris, the Latvian/Slovenian
|
||||
* municipalities, the UK's 231 micro-districts) collapse into the
|
||||
* region around them.
|
||||
* DISSOLVE— the merge is a real boolean union (`@turf/union`, polygon-
|
||||
* clipping): the shared boundary between the merged region and its
|
||||
* host is removed, producing a single clean polygon — not two
|
||||
* overlapping shapes. (Fallback if the union fails on a pair:
|
||||
* combine the rings into a MultiPolygon without dissolving; the
|
||||
* count of such fallbacks is reported.)
|
||||
* ITERATE — passes run smallest-area-first (small regions merge into their
|
||||
* neighbors, which grow and then absorb more). After each pass the
|
||||
* area/neighbor/centroid metrics are recomputed; it stops at the
|
||||
* fixed point (no small non-island region left) or at MAX_ITER.
|
||||
* IDENTITY— the host (the region merged INTO) keeps its own `id` and
|
||||
* `name`; the absorbed region's id is dropped. `properties.parent`
|
||||
* is unchanged, so the map code (WorldMap/App/protocol/map.ts)
|
||||
* keeps working untouched.
|
||||
*
|
||||
* Deterministic: fixed processing order (area, then id), deterministic
|
||||
* neighbor choice (distance, then -area, then id), deterministic boolean
|
||||
* union. Re-running on the coarsened file reaches the fixed point
|
||||
* immediately and rewrites a byte-identical file.
|
||||
*
|
||||
* Area model: the SAME planar approximation the validation test uses
|
||||
* (`scripts/regions.test.ts`) — `x = lon·111.32·cos(midLat)`,
|
||||
* `y = lat·110.574` km, shoelace per OUTER ring (holes ignored), each ring at
|
||||
* its own mean latitude — so the script's merge decisions and the test's
|
||||
* assertions measure the same quantity.
|
||||
*
|
||||
* Longitude handling: every ring is unwrapped to a continuous [0,360)-derived
|
||||
* space before its bbox/centroid is computed (the shortest-difference
|
||||
* "np.unwrap" scheme), which makes the one full-360° antimeridian-wrapping
|
||||
* feature (Antarctica's mainland ring) and any seam-straddling ring behave
|
||||
* correctly; cross-feature longitude gaps use the 360°-cyclic minimum.
|
||||
*
|
||||
* Output: features sorted by (parent, id) (the same comparator as
|
||||
* `scripts/generate-regions.mjs`), coordinates rounded to 4 decimal places,
|
||||
* single line of JSON + trailing newline. If the file would exceed the
|
||||
* ~5 MB guard, a light Douglas–Peucker pass (tolerances escalated through a
|
||||
* small table) brings it under ~4 MB before writing.
|
||||
*
|
||||
* Run: `npm run coarsen:regions`
|
||||
*/
|
||||
|
||||
import { readFileSync, writeFileSync } from 'node:fs';
|
||||
import path from 'node:path';
|
||||
import { fileURLToPath } from 'node:url';
|
||||
import { union } from '@turf/union';
|
||||
import { feature, featureCollection } from '@turf/helpers';
|
||||
|
||||
const here = path.dirname(fileURLToPath(import.meta.url));
|
||||
const root = path.resolve(here, '..');
|
||||
const FILE = path.join(root, 'public', 'regions.geo.json');
|
||||
|
||||
// --- parameters ---------------------------------------------------------------
|
||||
const AREA_FLOOR_KM2 = 10_000; // ~100×100 km floor for non-island regions
|
||||
const CLOSE_DEG = 0.2; // "spatially close" bbox gap (both lat and lon ≤ this; ≈≤22 km)
|
||||
const MAX_ITER = 20; // safety cap on fixed-point passes (spec: ~15)
|
||||
const SIZE_GUARD_KB = 5_120; // keep the committed file under ~5 MB
|
||||
const SIZE_TARGET_KB = 4_096; // …and land under ~4 MB once simplified
|
||||
const DP_STEPS = [0.05, 0.1, 0.2, 0.3, 0.5, 0.75, 1.0]; // Douglas–Peucker tolerances (degrees)
|
||||
const R4 = 4; // coordinate precision (decimal places, ≈11 m)
|
||||
const SLIVER_EPS_KM2 = 1e-6; // drop only truly-degenerate (≈zero-area) clipper slivers
|
||||
|
||||
// --- area model (identical to scripts/regions.test.ts) -------------------------
|
||||
const KM_LON = 111.32;
|
||||
const KM_LAT = 110.574;
|
||||
const rad = (deg) => (deg * Math.PI) / 180;
|
||||
|
||||
/** Shoelace area (km²) of one ring, measured at the ring's own mean latitude. */
|
||||
function ringAreaKm2(ring) {
|
||||
let lat = 0;
|
||||
for (const [, la] of ring) lat += la;
|
||||
const kx = KM_LON * Math.cos(rad(ring.length ? lat / ring.length : 0));
|
||||
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);
|
||||
}
|
||||
|
||||
/** Sum of a geometry's outer-ring areas (holes are lakes — ignored by design). */
|
||||
function geomAreaKm2(geom) {
|
||||
if (!geom) return 0;
|
||||
const polys = geom.type === 'Polygon' ? [geom.coordinates] : geom.coordinates;
|
||||
let total = 0;
|
||||
for (const poly of polys) total += ringAreaKm2(poly[0]);
|
||||
return total;
|
||||
}
|
||||
|
||||
// --- longitude unwrapping (antimeridian-safe) ----------------------------------
|
||||
|
||||
/**
|
||||
* Unwrap a ring's longitudes to a continuous real line (the "np.unwrap"
|
||||
* shortest-difference scheme, anchored at the first vertex's [0,360) value).
|
||||
* Returns { lons, full } — `full` when the unwrapped span is ≥ 300°, i.e. the
|
||||
* ring is a full-360° antimeridian band (Antarctica's mainland ring).
|
||||
*/
|
||||
function unwrapRing(ring) {
|
||||
const n = ring.length;
|
||||
const norm = (x) => ((x % 360) + 360) % 360; // → [0,360)
|
||||
const u = 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) (it accumulates),
|
||||
// so normalize it back before measuring the difference; otherwise a bogus
|
||||
// ~180° jump is inserted and the ring's span balloons to ~180°.
|
||||
const a = norm(u[i - 1]);
|
||||
const b = norm(ring[i][0]);
|
||||
const d = (((b - a) % 360) + 540) % 360 - 180; // shortest signed diff in (-180, 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 [0,360)-derived spaces. Tries the three 360° shifts of `b` so
|
||||
* different unwrap anchors reconcile; a `full` interval is close to everything.
|
||||
*/
|
||||
function lonGap(intA, intB) {
|
||||
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;
|
||||
}
|
||||
|
||||
// --- geometry helpers ----------------------------------------------------------
|
||||
const rN = (v, N) => Math.round(v * 10 ** N) / 10 ** N;
|
||||
|
||||
/** Round a ring to 4 dp, drop consecutive duplicates, and (re-)close it. */
|
||||
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 out; // degenerate; caller drops it
|
||||
return [...out, [...out[0]]];
|
||||
}
|
||||
|
||||
/**
|
||||
* Round every ring of a geometry to 4 dp, drop degenerate rings (<3 pts) and
|
||||
* empty polygons, keep the Polygon/MultiPolygon type (a single-part
|
||||
* MultiPolygon collapses to Polygon). Returns null if nothing usable survived.
|
||||
*/
|
||||
function roundAll(geom) {
|
||||
if (!geom || (geom.type !== 'Polygon' && geom.type !== 'MultiPolygon')) return null;
|
||||
const polys = (geom.type === 'Polygon' ? [geom.coordinates] : geom.coordinates)
|
||||
.map((poly) => poly.map((ring) => roundRing(ring)))
|
||||
.filter((poly) => poly.length >= 1 && poly.every((r) => r.length >= 3));
|
||||
if (!polys.length) return null;
|
||||
if (polys.length === 1 && geom.type === 'Polygon') return { type: 'Polygon', coordinates: polys[0] };
|
||||
return { type: 'MultiPolygon', coordinates: polys };
|
||||
}
|
||||
|
||||
/**
|
||||
* Normalize a union output (or fallback MultiPolygon): roundAll, then drop
|
||||
* truly-degenerate (≈zero-area, < SLIVER_EPS_KM2) polygons the clipper can
|
||||
* leave behind at shared boundaries. It never drops *every* part — a merge of
|
||||
* two sub-resolution (zero-area) micro-regions must still collapse into one
|
||||
* (degenerate) region rather than vanish. Returns null only when the input
|
||||
* itself had no usable ring (e.g. `null`).
|
||||
*/
|
||||
function normalizeGeom(geom) {
|
||||
const rounded = roundAll(geom);
|
||||
if (!rounded) return null;
|
||||
const all = rounded.type === 'Polygon' ? [rounded.coordinates] : rounded.coordinates;
|
||||
const kept = all.filter((poly) => ringAreaKm2(poly[0]) >= SLIVER_EPS_KM2);
|
||||
const polys = kept.length ? kept : all;
|
||||
if (polys.length === 1 && rounded.type === 'Polygon') return { type: 'Polygon', coordinates: polys[0] };
|
||||
return { type: 'MultiPolygon', coordinates: polys };
|
||||
}
|
||||
|
||||
/** Douglas–Peucker of an OPEN point sequence (keeps endpoints). */
|
||||
function dpOpen(pts, tol) {
|
||||
if (pts.length < 3) return pts;
|
||||
let maxD = 0;
|
||||
let idx = 0;
|
||||
const a = pts[0];
|
||||
const b = pts[pts.length - 1];
|
||||
for (let i = 1; i < pts.length - 1; i++) {
|
||||
const dx = b[0] - a[0];
|
||||
const dy = b[1] - a[1];
|
||||
const l2 = dx * dx + dy * dy;
|
||||
let t = l2 === 0 ? 0 : ((pts[i][0] - a[0]) * dx + (pts[i][1] - a[1]) * dy) / l2;
|
||||
t = Math.max(0, Math.min(1, t));
|
||||
const d = Math.hypot(pts[i][0] - (a[0] + t * dx), pts[i][1] - (a[1] + t * dy));
|
||||
if (d > maxD) {
|
||||
maxD = d;
|
||||
idx = i;
|
||||
}
|
||||
}
|
||||
if (maxD > tol) {
|
||||
const left = dpOpen(pts.slice(0, idx + 1), tol);
|
||||
const right = dpOpen(pts.slice(idx), tol);
|
||||
return left.concat(right.slice(1));
|
||||
}
|
||||
return [a, b];
|
||||
}
|
||||
|
||||
/** Douglas–Peucker a CLOSED ring at tolerance `tol` (0 = skip). */
|
||||
function dpRing(ring, tol) {
|
||||
if (tol <= 0 || ring.length < 4) return ring;
|
||||
let pts = ring;
|
||||
if (pts[0][0] === pts[pts.length - 1][0] && pts[0][1] === pts[pts.length - 1][1]) pts = pts.slice(0, -1);
|
||||
const s = dpOpen(pts, tol);
|
||||
if (s.length < 3) return ring;
|
||||
return [...s, [...s[0]]];
|
||||
}
|
||||
|
||||
/** Round (and optionally DP-simplify) every ring of a geometry. */
|
||||
function transformGeom(geom, tol) {
|
||||
const polys = (geom.type === 'Polygon' ? [geom.coordinates] : geom.coordinates)
|
||||
.map((poly) => poly.map((ring) => roundRing(ring, R4)).map((ring) => (tol > 0 ? dpRing(ring, tol) : ring)))
|
||||
.filter((poly) => poly.length >= 1 && poly.every((r) => r.length >= 3));
|
||||
if (!polys.length) return null;
|
||||
if (polys.length === 1 && geom.type === 'Polygon') return { type: 'Polygon', coordinates: polys[0] };
|
||||
return { type: 'MultiPolygon', coordinates: polys };
|
||||
}
|
||||
|
||||
// --- region record -------------------------------------------------------------
|
||||
|
||||
/**
|
||||
* A region under management. `lonInt` is the tight longitude interval in
|
||||
* [0,360)-derived unwrapped space (or `full` for a 360° band); `(clat, clon)`
|
||||
* is the area-weighted centroid of the LARGEST outer ring (the region's
|
||||
* "location"), unwrapped for its ring then wrapped to [-180,180) for
|
||||
* cyclic-distance use.
|
||||
*/
|
||||
class Region {
|
||||
constructor(f) {
|
||||
this.id = f.id;
|
||||
this.name = f.properties.name;
|
||||
this.parent = f.properties.parent;
|
||||
this.geom = f.geometry;
|
||||
this.rawGeom = null; // last pre-normalization union output (safety net for build())
|
||||
this.dead = false;
|
||||
this.metrics();
|
||||
}
|
||||
|
||||
metrics() {
|
||||
this.area = geomAreaKm2(this.geom);
|
||||
const polys = this.geom.type === 'Polygon' ? [this.geom.coordinates] : this.geom.coordinates;
|
||||
let latMin = Infinity;
|
||||
let latMax = -Infinity;
|
||||
let lonA = Infinity;
|
||||
let lonB = -Infinity;
|
||||
let lonFull = false;
|
||||
let bestRing = null;
|
||||
let bestArea = -1;
|
||||
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 } = unwrapRing(outer);
|
||||
if (full) lonFull = true;
|
||||
let a = Infinity;
|
||||
let b = -Infinity;
|
||||
for (const v of lons) {
|
||||
if (v < a) a = v;
|
||||
if (v > b) b = v;
|
||||
}
|
||||
lonA = Math.min(lonA, a);
|
||||
lonB = Math.max(lonB, b);
|
||||
const ar = ringAreaKm2(outer);
|
||||
if (ar > bestArea) {
|
||||
bestArea = ar;
|
||||
bestRing = outer;
|
||||
}
|
||||
}
|
||||
this.lonInt = { a: lonA, b: lonB, full: lonFull };
|
||||
this.latMin = latMin;
|
||||
this.latMax = latMax;
|
||||
// area-weighted centroid of the largest outer ring, in unwrapped space
|
||||
const { lons } = unwrapRing(bestRing);
|
||||
const lats = bestRing.map((p) => p[1]);
|
||||
const n = bestRing.length;
|
||||
let A = 0;
|
||||
let cx = 0;
|
||||
let cy = 0;
|
||||
for (let i = 0; i < n; i++) {
|
||||
const x1 = lons[i];
|
||||
const y1 = lats[i];
|
||||
const x2 = lons[(i + 1) % n];
|
||||
const y2 = lats[(i + 1) % n];
|
||||
const f = x1 * y2 - x2 * y1;
|
||||
A += f;
|
||||
cx += (x1 + x2) * f;
|
||||
cy += (y1 + y2) * f;
|
||||
}
|
||||
A /= 2;
|
||||
if (Math.abs(A) > 1e-9) {
|
||||
cx /= 6 * A;
|
||||
cy /= 6 * A;
|
||||
} else {
|
||||
cx = (lonA + lonB) / 2;
|
||||
cy = (latMin + latMax) / 2;
|
||||
}
|
||||
this.clon = (((cx + 180) % 360) + 360) % 360 - 180;
|
||||
this.clat = cy;
|
||||
}
|
||||
|
||||
/** Cyclic planar distance (km) to another region's centroid. */
|
||||
distKm(o) {
|
||||
let dlon = Math.abs(this.clon - o.clon) % 360;
|
||||
if (dlon > 180) dlon = 360 - dlon;
|
||||
const midLat = rad((this.clat + o.clat) / 2);
|
||||
return Math.hypot(dlon * KM_LON * Math.cos(midLat), (this.clat - o.clat) * KM_LAT);
|
||||
}
|
||||
|
||||
/** Bounding-box closeness to another same-space region (see CLOSE_DEG). */
|
||||
closeTo(o) {
|
||||
const latGap = this.latMax < o.latMin ? o.latMin - this.latMax : o.latMax < this.latMin ? this.latMin - o.latMax : 0;
|
||||
if (latGap > CLOSE_DEG) return false;
|
||||
return lonGap(this.lonInt, o.lonInt) <= CLOSE_DEG;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* A "degenerate" region is a zero-area artifact: after 4-dp rounding its only
|
||||
* ring has <3 distinct points (a line/point, e.g. a micro-municipality that
|
||||
* v0.13's Douglas–Peucker collapsed to `[A, B, A]`). It contributes no area,
|
||||
* so it can never be dissolved by the clipper (which returns null) nor kept
|
||||
* through ring-dropping (which loses the 2-point ring). Merging one is purely
|
||||
* an absorption: the host keeps its own geometry.
|
||||
*/
|
||||
const isDegenerate = (r) => r.area < SLIVER_EPS_KM2;
|
||||
|
||||
// --- main ----------------------------------------------------------------------
|
||||
function main() {
|
||||
const fc0 = JSON.parse(readFileSync(FILE, 'utf8'));
|
||||
const regions = fc0.features.map((f) => new Region(f));
|
||||
const byParent = new Map();
|
||||
for (const r of regions) {
|
||||
if (!byParent.has(r.parent)) byParent.set(r.parent, []);
|
||||
byParent.get(r.parent).push(r);
|
||||
}
|
||||
|
||||
const t0 = Date.now();
|
||||
console.log(`input: ${fc0.features.length} regions across ${byParent.size} countries (${(Buffer.byteLength(readFileSync(FILE)) / 1024).toFixed(0)} KB)`);
|
||||
console.log(`parameters: floor ${AREA_FLOOR_KM2.toLocaleString('en-US')} km2, close ${CLOSE_DEG} deg, max ${MAX_ITER} passes`);
|
||||
|
||||
const merges = []; // { from, fromName, fromArea, to, toName, toAreaAfter }
|
||||
let fallbackUnions = 0;
|
||||
|
||||
// The fixed-point loop. Each pass: every region that is small AND has a
|
||||
// close same-country neighbor merges into the nearest such neighbor
|
||||
// (nearest by centroid distance; tie → larger area → lexicographic id).
|
||||
for (let pass = 0; pass < MAX_ITER; pass++) {
|
||||
let skippedIsland = 0;
|
||||
let skippedGrew = 0;
|
||||
const items = [];
|
||||
for (const r of regions) {
|
||||
if (r.dead || r.area >= AREA_FLOOR_KM2) continue;
|
||||
const siblings = byParent.get(r.parent);
|
||||
for (const s of siblings) {
|
||||
if (s !== r && !s.dead && r.closeTo(s)) {
|
||||
items.push(r);
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
if (!items.length) {
|
||||
console.log(`after pass ${pass}: fixed point reached (no small non-island regions left)`);
|
||||
break;
|
||||
}
|
||||
items.sort((a, b) => (a.area !== b.area ? a.area - b.area : a.id < b.id ? -1 : 1));
|
||||
let merged = 0;
|
||||
for (const r of items) {
|
||||
if (r.dead) continue;
|
||||
if (r.area >= AREA_FLOOR_KM2) {
|
||||
skippedGrew++;
|
||||
continue; // absorbed a smaller region earlier this pass and crossed the floor
|
||||
}
|
||||
const siblings = byParent.get(r.parent);
|
||||
// Close same-country neighbors as of NOW (mid-pass): some may have died
|
||||
// earlier in this pass.
|
||||
const close = [];
|
||||
for (const s of siblings) if (s !== r && !s.dead && r.closeTo(s)) close.push(s);
|
||||
if (!close.length) {
|
||||
skippedIsland++;
|
||||
continue; // lost its last close neighbor this pass → island now → exempt
|
||||
}
|
||||
// Prefer a REAL (non-degenerate) host so real regions dissolve cleanly;
|
||||
// fall back to any close neighbor only when no real one is nearby.
|
||||
const realCands = close.filter((s) => !isDegenerate(s));
|
||||
const pool = realCands.length ? realCands : close;
|
||||
let host = null;
|
||||
for (const s of pool) {
|
||||
if (
|
||||
!host ||
|
||||
r.distKm(s) < r.distKm(host) ||
|
||||
(r.distKm(s) === r.distKm(host) &&
|
||||
(s.area !== host.area ? s.area > host.area : s.id < host.id))
|
||||
)
|
||||
host = s;
|
||||
}
|
||||
if (isDegenerate(r)) {
|
||||
// r is a zero-area artifact (line/point): it contributes no area, so the
|
||||
// merge is a pure absorption — the host keeps its own geometry (a real
|
||||
// host is untouched; if the host is also degenerate a cluster of dots
|
||||
// collapses to one). Never route degenerate input through the clipper
|
||||
// (returns null) or ring-dropping (would lose the 2-point ring the map
|
||||
// already renders).
|
||||
r.dead = true;
|
||||
merged++;
|
||||
merges.push({ from: r.id, fromName: r.name, fromArea: r.area, to: host.id, toName: host.name, toAreaAfter: host.area });
|
||||
continue;
|
||||
}
|
||||
if (isDegenerate(host)) {
|
||||
// r is real but the chosen host is a zero-area artifact: the host takes
|
||||
// on r's geometry (keeping its own id/name). No clipper needed.
|
||||
host.geom = r.geom;
|
||||
host.rawGeom = r.geom;
|
||||
host.metrics();
|
||||
r.dead = true;
|
||||
merged++;
|
||||
merges.push({ from: r.id, fromName: r.name, fromArea: r.area, to: host.id, toName: host.name, toAreaAfter: host.area });
|
||||
continue;
|
||||
}
|
||||
// Both real: dissolve via a boolean union; the host keeps its id/name
|
||||
// and the item vanishes. @turf/union@7 dispatches through geomEach, which
|
||||
// only understands a FeatureCollection / single Feature / bare geometry —
|
||||
// a raw array of features has no `.type` and throws "Unknown Geometry
|
||||
// Type". Wrap it.
|
||||
let unionGeom = null;
|
||||
let rawUnion = null;
|
||||
try {
|
||||
const u = union(featureCollection([feature(r.geom), feature(host.geom)]));
|
||||
rawUnion = u ? u.geometry : null;
|
||||
unionGeom = normalizeGeom(rawUnion);
|
||||
} catch (err) {
|
||||
console.error(` [warn] union failed for ${r.id} into ${host.id} (${err.message}); combining without dissolve`);
|
||||
fallbackUnions++;
|
||||
}
|
||||
if (!unionGeom) {
|
||||
// fallback: no dissolve — keep both shapes in one MultiPolygon
|
||||
const polys = [...(r.geom.type === 'Polygon' ? [r.geom.coordinates] : r.geom.coordinates), ...(host.geom.type === 'Polygon' ? [host.geom.coordinates] : host.geom.coordinates)];
|
||||
rawUnion = { type: 'MultiPolygon', coordinates: polys };
|
||||
unionGeom = normalizeGeom(rawUnion);
|
||||
if (!unionGeom) fallbackUnions++;
|
||||
}
|
||||
if (!unionGeom) {
|
||||
console.error(` [error] could not merge ${r.id} into ${host.id}; leaving ${r.id} as-is`);
|
||||
continue;
|
||||
}
|
||||
host.geom = unionGeom;
|
||||
host.rawGeom = rawUnion;
|
||||
host.metrics();
|
||||
r.dead = true;
|
||||
merged++;
|
||||
merges.push({ from: r.id, fromName: r.name, fromArea: r.area, to: host.id, toName: host.name, toAreaAfter: host.area });
|
||||
}
|
||||
const alive = regions.filter((r) => !r.dead).length;
|
||||
console.log(
|
||||
`pass ${pass + 1}: ${items.length} small non-island region(s) → ${merged} merged` +
|
||||
` (${skippedGrew} crossed the floor, ${skippedIsland} became island) → ${alive} regions remain`,
|
||||
);
|
||||
if (merged === 0) {
|
||||
// items exist but nothing could merge (all became islands this pass) → stable
|
||||
console.log(`pass ${pass + 1}: no merges possible — stable state`);
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
// --- assemble output ----------------------------------------------------------
|
||||
const alive = regions.filter((r) => !r.dead);
|
||||
const sortById = (a, b) =>
|
||||
a.parent !== b.parent ? (a.parent < b.parent ? -1 : 1) : a.id.localeCompare(b.id, 'en', { numeric: true });
|
||||
alive.sort(sortById);
|
||||
|
||||
const build = (tol) => {
|
||||
const feats = [];
|
||||
for (const r of alive) {
|
||||
// Never drop a region: if the simplified/normalized geometry degenerated,
|
||||
// fall back to the raw (pre-normalization) union output, then to the
|
||||
// untouched input geometry.
|
||||
const g =
|
||||
transformGeom(r.geom, tol) ??
|
||||
(r.rawGeom ? transformGeom(r.rawGeom, 0) ?? r.rawGeom : r.geom);
|
||||
feats.push({ type: 'Feature', id: r.id, properties: { name: r.name, parent: r.parent }, geometry: g });
|
||||
}
|
||||
return { type: 'FeatureCollection', features: feats };
|
||||
};
|
||||
|
||||
let out = build(0);
|
||||
let json = JSON.stringify(out);
|
||||
let sizeKB = Buffer.byteLength(json) / 1024;
|
||||
console.log(`\ncoarsened: ${fc0.features.length} → ${out.features.length} regions (${fc0.features.length - out.features.length} merged away)`);
|
||||
|
||||
let usedTol = 0;
|
||||
if (sizeKB > SIZE_GUARD_KB) {
|
||||
for (const t of DP_STEPS) {
|
||||
out = build(t);
|
||||
json = JSON.stringify(out);
|
||||
sizeKB = Buffer.byteLength(json) / 1024;
|
||||
usedTol = t;
|
||||
console.log(`DP ${t}: ${sizeKB.toFixed(1)} KB`);
|
||||
if (sizeKB < SIZE_TARGET_KB) break;
|
||||
}
|
||||
}
|
||||
writeFileSync(FILE, json + '\n');
|
||||
|
||||
// --- summary -------------------------------------------------------------------
|
||||
const areaOf = new Map();
|
||||
const counts = new Map();
|
||||
let maxA = 0;
|
||||
let maxR = null;
|
||||
for (const f of out.features) {
|
||||
const a = geomAreaKm2(f.geometry);
|
||||
areaOf.set(f.id, a);
|
||||
counts.set(f.properties.parent, (counts.get(f.properties.parent) ?? 0) + 1);
|
||||
if (a > maxA) {
|
||||
maxA = a;
|
||||
maxR = f;
|
||||
}
|
||||
}
|
||||
const ccounts = [...counts.values()].sort((a, b) => a - b);
|
||||
const median =
|
||||
ccounts.length % 2 ? ccounts[(ccounts.length - 1) / 2] : (ccounts[ccounts.length / 2 - 1] + ccounts[ccounts.length / 2]) / 2;
|
||||
const maxCountry = [...counts.entries()].sort((a, b) => b[1] - a[1])[0];
|
||||
|
||||
// islands = small regions with no close same-country neighbor in the FINAL set
|
||||
const finalByParent = new Map();
|
||||
for (const f of out.features) {
|
||||
if (!finalByParent.has(f.properties.parent)) finalByParent.set(f.properties.parent, []);
|
||||
finalByParent.get(f.properties.parent).push(f);
|
||||
}
|
||||
// rebuild final metrics (light: only need island flag on the < FLOOR set)
|
||||
const finalRegions = out.features.map((f) => new Region(f));
|
||||
const finalByParent2 = new Map();
|
||||
for (const r of finalRegions) {
|
||||
if (!finalByParent2.has(r.parent)) finalByParent2.set(r.parent, []);
|
||||
finalByParent2.get(r.parent).push(r);
|
||||
}
|
||||
let smallIslands = 0;
|
||||
let smallNonIslands = 0;
|
||||
const islandSamples = [];
|
||||
for (const r of finalRegions) {
|
||||
if (r.area >= AREA_FLOOR_KM2) continue;
|
||||
let hasNeighbor = false;
|
||||
for (const s of finalByParent2.get(r.parent)) {
|
||||
if (s !== r && r.closeTo(s)) {
|
||||
hasNeighbor = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
if (hasNeighbor) smallNonIslands++;
|
||||
else {
|
||||
smallIslands++;
|
||||
if (islandSamples.length < 12) islandSamples.push(`${r.id} ${r.name} (${Math.round(r.area)} km2)`);
|
||||
}
|
||||
}
|
||||
|
||||
console.log(`wrote ${FILE} — ${sizeKB.toFixed(1)} KB (${(sizeKB / 1024).toFixed(2)} MB)` + (usedTol ? ` [DP @ ${usedTol}°]` : ''));
|
||||
console.log(`per-country count: min ${ccounts[0]} / median ${median} / max ${ccounts[ccounts.length - 1]} (max: ${maxCountry[0]})`);
|
||||
console.log(`max region: ${maxR.id} (${maxR.properties.name}) ≈ ${Math.round(maxA).toLocaleString('en-US')} km2`);
|
||||
console.log(`small (<${AREA_FLOOR_KM2.toLocaleString('en-US')} km2) in final set: ${smallIslands + smallNonIslands} — ${smallIslands} islands (exempt) / ${smallNonIslands} non-island residuals`);
|
||||
if (islandSamples.length) console.log(`island samples: ${islandSamples.join(', ')}`);
|
||||
console.log(`fallback (non-dissolved) unions: ${fallbackUnions}`);
|
||||
console.log(`merge log (${merges.length} merges): first 15:`);
|
||||
for (const m of merges.slice(0, 15)) {
|
||||
console.log(` ${m.from} (${m.fromName}, ${Math.round(m.fromArea)} km2) → ${m.to} (${m.toName}, now ${Math.round(m.toAreaAfter)} km2)`);
|
||||
}
|
||||
const logPath = '/tmp/opencode/coarsen-log.txt';
|
||||
writeFileSync(logPath, merges.map((m) => `${m.from}\t${m.fromName}\t${Math.round(m.fromArea)}\t${m.to}\t${m.toName}\t${Math.round(m.toAreaAfter)}`).join('\n') + '\n');
|
||||
console.log(`full merge log → ${logPath}; elapsed ${((Date.now() - t0) / 1000).toFixed(1)}s`);
|
||||
}
|
||||
|
||||
main();
|
||||
+222
-6
@@ -1,12 +1,16 @@
|
||||
/**
|
||||
* scripts/regions.test.ts — validation for the committed `public/regions.geo.json`.
|
||||
*
|
||||
* The dataset is now REAL named sub-national administrative regions (Natural
|
||||
* Earth admin-1: states, provinces, governorates, oblasts, …) rather than the
|
||||
* old geometric grid — 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`).
|
||||
* 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`).
|
||||
*
|
||||
* This test is self-contained (no import of the generator): it re-implements
|
||||
* the same planar area model the generator/analysis use, so the area-based
|
||||
@@ -109,6 +113,99 @@ const countByParent = new Map<string, number>();
|
||||
for (const f of regions.features)
|
||||
countByParent.set(f.properties.parent, (countByParent.get(f.properties.parent) ?? 0) + 1);
|
||||
|
||||
// --- 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');
|
||||
@@ -188,6 +285,89 @@ describe('regions.geo.json', () => {
|
||||
);
|
||||
});
|
||||
|
||||
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('has no small enclosed holes left (the v0.15 cleanup filled them); only real water bodies remain', () => {
|
||||
// v0.15 cleanup (scripts/cleanup-regions.mjs): every enclosed hole (inner
|
||||
// ring) smaller than the threshold was dropped so each region is solid;
|
||||
// only genuine water bodies (holes >= the threshold) survive. The big real
|
||||
// lakes (Great Lakes, Caspian, Aral, Lake Superior, …) were already
|
||||
// dissolved by the v0.14 coarsening, so the surviving holes are few and
|
||||
// large. This guards the fix: a re-introduction of the tiny artifacts
|
||||
// (thousands of < threshold holes) fails here.
|
||||
const HOLE_MIN_KM2 = 1000; // keep in sync with cleanup-regions.mjs HOLE_AREA_MAX_KM2
|
||||
let holeCount = 0;
|
||||
let smallHoles = 0;
|
||||
let maxHole = 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++) {
|
||||
const hole = poly[i];
|
||||
let lat = 0;
|
||||
for (const [, la] of hole) lat += la;
|
||||
const area = ringAreaKm2(hole, hole.length ? lat / hole.length : 0);
|
||||
holeCount++;
|
||||
if (area > maxHole) maxHole = area;
|
||||
if (area < HOLE_MIN_KM2) {
|
||||
smallHoles++;
|
||||
if (smallHoles <= 10) console.log(` small hole ${f.id} ≈ ${Math.round(area)} km2`);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
expect(
|
||||
smallHoles,
|
||||
`${smallHoles} enclosed hole(s) below ${HOLE_MIN_KM2} km2 remain — the v0.15 cleanup should have filled them`,
|
||||
).toBe(0);
|
||||
expect(
|
||||
holeCount <= 20,
|
||||
`${holeCount} holes remain — expected only a handful of real water bodies`,
|
||||
).toBe(true);
|
||||
console.log(
|
||||
`\n enclosed holes: ${holeCount} remain (all >= ${HOLE_MIN_KM2} km2, largest ${Math.round(maxHole).toLocaleString('en-US')} km2) — small artifacts filled by the v0.15 cleanup`,
|
||||
);
|
||||
});
|
||||
|
||||
it('sums to within [40%, 175%] 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
|
||||
@@ -224,4 +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