arthur/js/selftest.js

// Assertions over the stages below detection. Runs in the browser so the exact
// module graph the tool uses is what gets tested.
//
// The ring-simplicity check exists because "fixed topology" is load-bearing in
// docs/roto-puppet.md: because hold parts CUT between poses rather than
// interpolating, a ring whose vertex order is wrong self-intersects and renders
// as blocks meeting at corners. It is invisible at some vertex counts and obvious
// at others, so it needs an assertion rather than an eyeball.

import { LIPS_OUTER, LIPS_INNER, FACE_OVAL, RIGID, subsampleSlots, subsampleRing } from './landmarks.js';
import { fitSimilarity, applySim, procrustesMean, smoothTransforms } from './mathutil.js';
import { stabilize, toRasterRing, selectKeys, activeKey } from './pipeline.js';
import { IndexedRaster, hexToRgb } from './raster.js';
import { writeTake } from './take.js';
import { synthDense } from './synth.js';

const results = [];
const ok = (name, cond, detail = '') => results.push({ name, pass: !!cond, detail });

/* ---- geometry helpers ---- */

function segmentsCross(a, b, c, d) {
  const o = (p, q, r) => Math.sign((q.x - p.x) * (r.y - p.y) - (q.y - p.y) * (r.x - p.x));
  const o1 = o(a, b, c), o2 = o(a, b, d), o3 = o(c, d, a), o4 = o(c, d, b);
  return o1 !== o2 && o3 !== o4 && o1 !== 0 && o2 !== 0 && o3 !== 0 && o4 !== 0;
}

// A closed ring is simple if no pair of non-adjacent edges crosses.
function ringSelfIntersections(pts) {
  const n = pts.length, hits = [];
  for (let i = 0; i < n; i++) {
    for (let j = i + 1; j < n; j++) {
      if (i === j || (j + 1) % n === i || (i + 1) % n === j) continue;
      if (segmentsCross(pts[i], pts[(i + 1) % n], pts[j], pts[(j + 1) % n])) hits.push([i, j]);
    }
  }
  return hits;
}

const spreadX = (frames, slot) => {
  const xs = frames.map((f) => f[slot].x);
  return Math.max(...xs) - Math.min(...xs);
};

/* ---- the tests ---- */

export function run() {
  results.length = 0;

  // tables
  ok('LIPS_OUTER has 20 distinct ids', new Set(LIPS_OUTER).size === 20);
  ok('LIPS_INNER has 20 distinct ids', new Set(LIPS_INNER).size === 20);
  ok('FACE_OVAL has 36 distinct ids', new Set(FACE_OVAL).size === 36);
  ok('RIGID excludes every lip vertex',
     !RIGID.some((i) => LIPS_OUTER.includes(i) || LIPS_INNER.includes(i)),
     'a moving feature in the rigid set bleeds performance into stabilisation');

  // subsampling preserves order and count at every budget
  for (let n = 4; n <= 16; n += 2) {
    const s = subsampleSlots(20, n);
    const mono = s.every((v, i) => i === 0 || v > s[i - 1]);
    ok(`subsampleSlots(20,${n}) is strictly increasing, n=${n}`, mono && s.length === n, s.join(','));
  }
  ok('subsampleRing agrees with subsampleSlots',
     subsampleRing(LIPS_OUTER, 8).join(',') === subsampleSlots(20, 8).map((s) => LIPS_OUTER[s]).join(','));

  const dense = synthDense(72);

  // rings must be simple at EVERY vertex budget, on every frame
  for (const [label, table] of [['outer', LIPS_OUTER], ['inner', LIPS_INNER]]) {
    let worst = null;
    for (let n = 4; n <= 16 && !worst; n += 2) {
      const slots = subsampleSlots(table.length, n);
      for (let f = 0; f < dense.length; f++) {
        const pts = slots.map((s) => dense[f][table[s]]);
        const hits = ringSelfIntersections(pts);
        if (hits.length) { worst = `verts=${n} frame=${f} edges ${JSON.stringify(hits[0])}`; break; }
      }
    }
    ok(`${label} ring is simple at every vertex budget`, !worst, worst || '');
  }

  // FACE_OVAL traversal: never checked before, and a wrong ordering here shows up
  // as a lumpy plate rather than an obvious bowtie, so it needs asserting.
  {
    let bad = null;
    for (let f = 0; f < dense.length && !bad; f++) {
      const h = ringSelfIntersections(FACE_OVAL.map((i) => dense[f][i]));
      if (h.length) bad = `frame ${f} edges ${JSON.stringify(h[0])}`;
    }
    ok('FACE_OVAL is a simple ring on every frame', !bad, bad || '');
  }

  // similarity fit recovers a known transform
  const src = [{ x: 0, y: 0 }, { x: 1, y: 0 }, { x: 0, y: 1 }, { x: 2, y: 3 }];
  const truth = { s: 1.7, theta: 0.6, tx: 4, ty: -2 };
  const dst = src.map((p) => applySim(truth, p));
  const got = fitSimilarity(src, dst);
  ok('fitSimilarity recovers a known transform',
     Math.abs(got.s - truth.s) < 1e-9 && Math.abs(got.theta - truth.theta) < 1e-9 &&
     Math.abs(got.tx - truth.tx) < 1e-9 && Math.abs(got.ty - truth.ty) < 1e-9,
     `s=${got.s.toFixed(6)} th=${got.theta.toFixed(6)}`);

  // stabilisation: head motion out, mouth motion kept
  const stab = stabilize(dense, 0);
  const rawSpread = spreadX(dense, 133);
  const stabSpread = (() => {
    const xs = stab.eyes.map((e) => e[0].x);
    return Math.max(...xs) - Math.min(...xs);
  })();
  ok('stabilisation removes >90% of head translation',
     stabSpread < rawSpread * 0.1, `raw ${rawSpread.toFixed(4)} -> ${stabSpread.toFixed(4)}`);
  const apRange = Math.max(...stab.aperture) - Math.min(...stab.aperture);
  ok('stabilisation preserves mouth motion', apRange > 0.05, `aperture range ${apRange.toFixed(4)}`);

  // ASPECT: a shape that is circular in PIXEL space must stay circular in raster
  // space. MediaPipe normalises x by width and y by height, so for a portrait
  // frame equal normalised numbers are unequal pixel distances; feeding those
  // straight through stretches everything horizontally by H/W. This asserts the
  // isotropic conversion, and fails at ~1.78 for a 1080x1920 clip without it.
  for (const [W, H] of [[1080, 1920], [1920, 1080], [640, 640]]) {
    const aspect = W / H;
    const N = 24, cx = 0.5, cy = 0.5, rPx = 200;
    // a true circle of radius rPx, expressed in MediaPipe normalised coords
    const circleFrames = [];
    for (let t = 0; t < 4; t++) {
      const pts = new Array(478).fill(null).map(() => ({ x: 0.5, y: 0.5, z: 0 }));
      RIGID.forEach((id, k) => {
        const a = (k / RIGID.length) * Math.PI * 2;
        pts[id] = { x: cx + (120 * Math.cos(a)) / W, y: cy + (120 * Math.sin(a)) / H, z: 0 };
      });
      LIPS_OUTER.forEach((id, k) => {
        const a = -(k / LIPS_OUTER.length) * Math.PI * 2;
        pts[id] = { x: cx + (rPx * Math.cos(a)) / W, y: cy + (rPx * Math.sin(a)) / H, z: 0 };
      });
      FACE_OVAL.forEach((id, k) => {
        const a = -(k / FACE_OVAL.length) * Math.PI * 2;
        pts[id] = { x: cx + (420 * Math.cos(a)) / W, y: cy + (420 * Math.sin(a)) / H, z: 0 };
      });
      circleFrames.push(pts);
    }
    const st2 = stabilize(circleFrames, 0, aspect);
    const ring = toRasterRing(st2.outer[0], LIPS_OUTER, 16, (p) => p);
    const xs = ring.map((p) => p.x), ys = ring.map((p) => p.y);
    const ratio = (Math.max(...xs) - Math.min(...xs)) / (Math.max(...ys) - Math.min(...ys));
    ok(`circle stays circular at ${W}x${H}`, Math.abs(ratio - 1) < 0.02,
       `w/h ratio ${ratio.toFixed(4)}`);
  }

  // key selection
  const xf = (p) => ({ x: p.x * 320, y: p.y * 200 });
  const shapes = stab.outer.map((r) => toRasterRing(r, LIPS_OUTER, 8, xf));
  const sel = selectKeys(shapes, { minHold: 2, distThresh: 0.6, velSmooth: 3, exposure: 2 });
  ok('keys are strictly increasing in f', sel.keys.every((k, i) => i === 0 || k.f > sel.keys[i - 1].f));
  ok('keys respect the minimum hold',
     sel.keys.every((k, i) => i === 0 || k.src - sel.keys[i - 1].src >= 2));
  ok('keys land on the exposure grid', sel.keys.every((k) => k.f % 2 === 0));
  ok('selection reduces candidates', sel.keys.length < sel.candidates.length,
     `${sel.candidates.length} candidates -> ${sel.keys.length} keys`);
  ok('first key is frame 0', sel.keys[0].f === 0);
  ok('activeKey holds between keys',
     activeKey(sel.keys, sel.keys[1].f - 1).f === sel.keys[0].f);

  // rasteriser: indexed, hard-edged, no blending
  const r = new IndexedRaster(64, 48);
  r.clear(0);
  r.fillPoly([{ x: 8, y: 8 }, { x: 56, y: 8 }, { x: 56, y: 40 }, { x: 8, y: 40 }], 2);
  const present = new Set(r.buf);
  ok('raster contains only written indices', present.size === 2 && present.has(0) && present.has(2),
     `indices ${[...present].join(',')}`);
  let count = 0;
  for (const v of r.buf) if (v === 2) count++;
  ok('axis-aligned rect fills the exact pixel count', count === 48 * 32, `${count} vs ${48 * 32}`);
  const pal = ['#000000', '#ffffff', '#ff8800'];
  const img = r.toImageData(pal, 2);
  const seen = new Set();
  for (let i = 0; i < img.data.length; i += 4) {
    seen.add(`${img.data[i]},${img.data[i + 1]},${img.data[i + 2]}`);
  }
  const allowed = new Set(pal.map((h) => hexToRgb(h).join(',')));
  ok('palette expansion introduces no intermediate colours',
     [...seen].every((c) => allowed.has(c)), `${seen.size} distinct colours`);

  // take writer round-trip
  const take = {
    name: 'test', frames: 72, width: 320, height: 200, exposure: 2,
    palette: [{ name: 'bg' }, { name: 'skin' }],
    slot: { x: 160, y: 100 },
    parts: [
      { name: 'head', kind: 'plate', z: 0, interp: 'hold', keys: [{ f: 0, plate: 0 }] },
      { name: 'mouth', kind: 'poly', z: 30, color: 'skin', interp: 'hold',
        keys: sel.keys.map((k) => ({ f: k.f, src: k.src, pts: shapes[k.src] })) },
    ],
  };
  const text = writeTake(take);
  const keyLines = text.split('\n').filter((l) => l.startsWith('key') && l.includes('n='));
  ok('every key line declares n= matching its point count',
     keyLines.every((l) => {
       const n = +l.match(/n=(\d+)/)[1];
       const pts = l.split(/n=\d+\s+/)[1].trim().split(/\s+/);
       return pts.length === n;
     }), `${keyLines.length} key lines`);
  ok('take declares a plate and a part table',
     /^plate\s+0/m.test(text) && /^part\s+mouth/m.test(text));
  ok('coordinates are integers', !/-?\d+\.\d/.test(text.split('\n').filter((l) => l.startsWith('key')).join('')));

  return results;
}