/*
 * yapf.js — YAPF encoder (v1) and decoder (v1 and v2) in plain JavaScript.
 *
 * Copyright 2026 Nexoniarz — Apache License 2.0.
 *
 * Works in browsers, Node.js, Figma plugins and VS Code webviews; no
 * dependencies.  Produces exactly the same bytes as the C library.
 *
 *   const img  = YAPF.decode(bytes);    // Uint8Array → image
 *   const file = YAPF.encode(img);      // image → Uint8Array
 *   const rgba = YAPF.toRGBA(img);      // any channel count → RGBA pixels
 *
 *   const tex  = YAPF.decodeTexture(bytes);          // any v1 / v2 file
 *   const view = YAPF.textureToRGBA(tex, surface);   // { width, height, rgba }
 *
 * An image is { width, height, channels (1–4), pixels: Uint8Array,
 *               gpuFormat, flags, mipLevels, mips: [Uint8Array, …] }.
 * Version 2 textures (GPU blocks, 16-bit / float, cubes, arrays, volumes,
 * animation) are decoded by decodeTexture; encoding writes version 1.
 * The specification: yapf.h (v1) and docs/FORMAT.md (v2).
 */
(function (root, factory) {
  if (typeof module === 'object' && module.exports) module.exports = factory();
  else root.YAPF = factory();
}(typeof self !== 'undefined' ? self : this, function () {
  'use strict';

  const TILE = 64, TILE_PX = TILE * TILE, GROUP = 8, BAND = 8, RING = 16;
  const MAX_GROUPS = TILE_PX / GROUP, MAX_DIM = 65535, MAX_MIPS = 16;
  const STORED = 0x80, SUBGREEN = 0x10, NIB_REPEAT = 9;
  const F_LEFT = 0, F_GRAD = 1, F_UPRIGHT = 2, F_UPAVG = 3, F_UP = 16;
  const NIB_GROUPS = [1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 3, 4, 8, 16, 32, 64];
  const RUN_LENS = [2, 3, 4, 8, 16, 32, 64];
  /* Encoder try order: cheapest to decode first, ties go to the earlier. */
  const FILTERS = [F_UP, F_UP + 1, F_UP + 2, F_UP + 3, F_UP + 4, F_UP + 5,
                   F_UP + 6, F_UP + 7, F_UPRIGHT, F_UPAVG, F_LEFT, F_GRAD];

  const GPU = { RGBA8: 0, RGB8: 1, RG8: 2, R8: 3, SRGB8_A8: 4, SRGB8: 5 };
  const FLAG = { PREMULT_ALPHA: 1, SRGB: 2 };

  const ZERO_ROW = new Uint8Array(TILE + 1);

  const zz   = (r) => ((r << 1) ^ ((r << 24) >> 31)) & 255;  /* r is 0..255 */
  const unzz = (z) => ((z >>> 1) ^ -(z & 1)) & 255;
  const width = (z) => (z === 0 ? 0 : 32 - Math.clz32(z));
  const s8 = (v) => (v << 24) >> 24;
  const filterValid = (f) => f <= F_UPAVG || (f >= F_UP && f < F_UP + 8);
  const upK = (f) => (f >= F_UP ? f - F_UP + 1 : 1);

  function corrupt() { throw new YapfError('corrupt', 'corrupt file'); }

  /* ── Version 2: textures (decoding) ───────────────────────────────── */

  const ENTROPY = 0x20, NOXFORM = 0x40, BLOCK_TILE = 16;
  const HUFF_BITS = 11, HUFF_SIZE = 1 << HUFF_BITS, SLOTS = 48, CTXS = 7;
  const NEED = { WIDE: 1, BLOCKS: 2, ENTROPY: 4, LAYOUT: 8, FRAMES: 16, ALL: 31 };
  const r16 = (b, p) => b[p] | (b[p + 1] << 8);
  const r64 = (b, p) => r32(b, p) + r32(b, p + 4) * 4294967296;

  class YapfError extends Error {
    constructor(code, msg) { super('YAPF: ' + msg); this.code = code; }
  }
  const fail = (code, msg) => { throw new YapfError(code, msg); };
  const bad = () => fail('corrupt', 'corrupt file');

  /* yapf-sum: 64-bit lanes kept as [hi, lo] uint32 pairs. */
  const KH = 0x9E3779B9, KL = 0x7F4A7C15;
  function mul64(ah, al, bh, bl) {            /* (a · b) mod 2^64 */
    const a0 = al & 0xFFFF, a1 = al >>> 16, b0 = bl & 0xFFFF, b1 = bl >>> 16;
    const p00 = a0 * b0, p01 = a0 * b1, p10 = a1 * b0, p11 = a1 * b1;
    const mid = (p00 >>> 16) + (p01 & 0xFFFF) + (p10 & 0xFFFF);
    const lo = ((mid & 0xFFFF) * 65536 + (p00 & 0xFFFF)) >>> 0;
    const hi = (p11 + (p01 >>> 16) + (p10 >>> 16) + Math.floor(mid / 65536) +
                Math.imul(ah, bl) + Math.imul(al, bh)) >>> 0;
    return [hi, lo];
  }
  function checksum(b, p, n) {
    const lanes = [];
    for (let i = 0; i < 4; i++) {
      const [h, l] = mul64(0, i + 1, KH, KL);
      lanes.push([(h ^ Math.floor(n / 4294967296)) >>> 0, (l ^ (n >>> 0)) >>> 0]);
    }
    const words = Math.ceil(n / 8);
    for (let j = 0; j < words; j++) {
      const q = p + j * 8;
      let wl, wh;
      if (q + 8 <= p + n) { wl = r32(b, q); wh = r32(b, q + 4); }
      else {
        const t = new Uint8Array(8); t.set(b.subarray(q, p + n));
        wl = r32(t, 0); wh = r32(t, 4);
      }
      const a = lanes[j & 3];
      const [h, l] = mul64((a[0] ^ wh) >>> 0, (a[1] ^ wl) >>> 0, KH, KL);
      a[0] = h; a[1] = (l ^ h) >>> 0;                    /* a ^= a >> 32 */
    }
    const rot = (x, r) => r === 32 ? [x[1], x[0]]
      : [((x[0] << r) | (x[1] >>> (32 - r))) >>> 0, ((x[1] << r) | (x[0] >>> (32 - r))) >>> 0];
    const r1 = rot(lanes[1], 16), r2 = rot(lanes[2], 32), r3 = rot(lanes[3], 48 - 32);
    const r3b = [r3[1], r3[0]];                            /* rotl 48 = rotl 16 then swap */
    let hh = (lanes[0][0] ^ r1[0] ^ r2[0] ^ r3b[0]) >>> 0, hl = (lanes[0][1] ^ r1[1] ^ r2[1] ^ r3b[1]) >>> 0;
    [hh, hl] = mul64(hh, hl, KH, KL);
    return (hl ^ hh) >>> 0;
  }

  /* Huffman code table → lut[off .. off + 2048) (length << 8 | symbol). */
  function huffTable(b, p, end, lut, off) {
    if (p >= end) bad();
    const n = b[p++] + 1, nbytes = (n + 1) >> 1;
    if (end - p < nbytes) bad();
    const len = new Uint8Array(n), count = new Uint32Array(HUFF_BITS + 2);
    let kraft = 0;
    for (let i = 0; i < n; i++) {
      const l = (b[p + (i >> 1)] >> ((i & 1) * 4)) & 15;
      if (l > HUFF_BITS) bad();
      len[i] = l; count[l]++;
      if (l) kraft += HUFF_SIZE >> l;
    }
    if ((n & 1) && (b[p + (n >> 1)] >> 4)) bad();
    if (kraft === 0 || kraft > HUFF_SIZE) bad();
    p += nbytes;
    const next = new Uint32Array(HUFF_BITS + 2);
    let code = 0;
    count[0] = 0;
    for (let l = 1; l <= HUFF_BITS; l++) { code = (code + count[l - 1]) << 1; next[l] = code; }
    for (let s = 0; s < n; s++) {
      const l = len[s];
      if (!l) continue;
      let c = next[l]++, r = 0;
      for (let i = 0; i < l; i++) { r = (r << 1) | (c & 1); c >>= 1; }
      for (let k = r; k < HUFF_SIZE; k += 1 << l) lut[off + k] = (l << 8) | s;
    }
    return p;
  }

  /* Code book → per slot one Uint16Array of 7 × 2048 entries. */
  function readBook(b, p, len) {
    const end = p + len;
    if (len < 2) bad();
    const n = r16(b, p);
    p += 2;
    if (n === 0 || n > SLOTS * CTXS) bad();
    const book = new Array(SLOTS).fill(null), seen = new Uint8Array(SLOTS * CTXS);
    for (let i = 0; i < n; i++) {
      if (end - p < 3) bad();
      const slot = b[p], ctx = b[p + 1];
      if (slot >= SLOTS || ctx >= CTXS || seen[slot * CTXS + ctx]) bad();
      seen[slot * CTXS + ctx] = 1;
      if (!book[slot]) book[slot] = new Uint16Array(CTXS * HUFF_SIZE);
      p = huffTable(b, p + 2, end, book[slot], ctx * HUFF_SIZE);
    }
    if (p !== end) bad();
    return book;
  }

  /* Context of a residual from the folded residuals left + above. */
  const ctxOf = (s) => (s > 0) + (s > 2) + (s > 6) + (s > 14) + (s > 30) + (s > 62);

  /* Entropy plane payload: filters, u16 length, context-coded residuals. */
  function huffPlane(b, p, end, z, tw, th, book, slot) {
    const nb = (th + BAND - 1) >> 3;
    if (!book || !book[slot] || end - p < nb + 2) bad();
    const filt = b.subarray(p, p + nb);
    for (let i = 0; i < nb; i++) if (!filterValid(filt[i])) bad();
    p += nb;
    const L = r16(b, p);
    p += 2;
    if (end - p < L) bad();
    const lut = book[slot], se = p + L;
    let buf = 0, bits = 0, pos = p, used = 0, i = 0;
    for (let y = 0; y < th; y++)
      for (let x = 0; x < tw; x++, i++) {
        while (bits <= 24) { buf |= (pos < se ? b[pos] : 0) << bits; pos++; bits += 8; }
        const s = (x ? z[i - 1] : 0) + (y ? z[i - tw] : 0);
        const e = lut[(ctxOf(s) << HUFF_BITS) | (buf & (HUFF_SIZE - 1))];
        if (!e) bad();
        const n = e >> 8;
        buf >>>= n; bits -= n; used += n;
        z[i] = e & 255;
      }
    if (Math.ceil(used / 8) !== L) bad();
    z.fill(0, tw * th, tw * th + GROUP);
    return { p: se, filt };
  }

  /* Wide samples: byte planes, transforms at the sample width. */
  function decodeTileWide(b, p, end, out, imgW, tx, ty, tw, th, ch, sample, book) {
    const sb = sample === 3 ? 4 : 2, bits = 8 * sb, isf = sample >= 2, np = ch * sb;
    const half = bits === 32 ? 0x80000000 : 0x8000;
    const mod = bits === 32 ? (x) => x >>> 0 : (x) => x & 0xFFFF;
    const sar1 = (v) => mod((v >>> 1) | (v & half));
    if (end <= p) bad();
    const hdr = b[p++];
    if (hdr === STORED) {
      if (end - p !== tw * th * ch * sb) bad();
      for (let y = 0; y < th; y++) {
        const d = ((ty + y) * imgW + tx) * ch;
        for (let i = 0; i < tw * ch; i++, p += sb)
          out[d + i] = sb === 2 ? r16(b, p) : r32(b, p);
      }
      return;
    }
    if (hdr & 0x8F) bad();
    if ((hdr & NOXFORM) && (hdr & SUBGREEN)) bad();
    if (ch < 3 && (hdr & (NOXFORM | SUBGREEN))) bad();
    const xf = ch < 3 ? 2 : (hdr & NOXFORM) ? 2 : (hdr & SUBGREEN) ? 1 : 0;
    const tsel = ch < 3 ? 0 : xf;
    if (end - p < 2) bad();
    const cmask = r16(b, p);
    p += 2;
    if (cmask >> np) bad();
    let emask = 0;
    if (hdr & ENTROPY) {
      if (end - p < 2 || !book) bad();
      emask = r16(b, p);
      p += 2;
      if ((emask >> np) || (emask & cmask)) bad();
    }
    const RL = TILE + 1, PL = TILE * RL;
    const planes = new Uint8Array(np * PL), z = new Uint8Array(TILE_PX + GROUP);
    for (let pl = 0; pl < np; pl++) {
      if (!(cmask & (1 << pl))) continue;
      if (p >= end) bad();
      planes.fill(b[p++], pl * PL, (pl + 1) * PL);
    }
    for (let pl = 0; pl < np; pl++) {
      if (cmask & (1 << pl)) continue;
      z.fill(0);
      const r = (emask & (1 << pl)) ? huffPlane(b, p, end, z, tw, th, book, tsel * 16 + pl)
                                    : unpackPlane(b, p, end, z, tw, th);
      p = r.p;
      const base = pl * PL;
      for (let y = 0; y < th; y++) {
        const f = r.filt[y >> 3], k = upK(f);
        unfilterRow(f, planes, base + y * RL,
                    y ? planes : ZERO_ROW, y ? base + (y - 1) * RL : 0,
                    y >= k ? planes : ZERO_ROW, y >= k ? base + (y - k) * RL : 0,
                    z, y * tw, tw);
      }
    }
    if (p !== end) bad();
    const v = [0, 0, 0, 0];
    for (let y = 0; y < th; y++) {
      const d0 = ((ty + y) * imgW + tx) * ch, r0 = y * RL;
      for (let x = 0; x < tw; x++) {
        for (let c = 0; c < ch; c++) {
          let a = 0;
          for (let k = 0; k < sb; k++) a = a * 256 + planes[(c * sb + k) * PL + r0 + x];
          v[c] = a;
        }
        if (xf === 0) {
          const o = mod(v[1] - half), q = mod(v[2] - half), t = mod(v[0] - sar1(q));
          const g = mod(q + t), bb = mod(t - sar1(o));
          v[0] = mod(bb + o); v[1] = g; v[2] = bb;
        } else if (xf === 1) {
          const g = v[0];
          v[0] = mod(v[1] + g - half); v[2] = mod(v[2] + g - half); v[1] = g;
        }
        for (let c = 0; c < ch; c++) {
          let s = v[c];
          if (isf) s = (s & half) ? mod(s ^ half) : mod(~s);
          out[d0 + x * ch + c] = s;
        }
      }
    }
  }

  /* GPU block tile: raw, or packed lane by lane with the book. */
  function decodeBlockTile(b, p, end, packed, out, o0, rowb, tbw, tbh, S, book) {
    const n = tbw * tbh;
    if (!packed) {
      if (end - p !== n * S) bad();
      for (let r = 0; r < tbh; r++) out.set(b.subarray(p + r * tbw * S, p + (r + 1) * tbw * S), o0 + r * rowb);
      return;
    }
    if (!book) bad();
    let buf = 0, bits = 0, pos = p, used = 0;
    for (let k = 0; k < S; k++) {
      const lut = book[k];
      if (!lut) bad();
      for (let i = 0; i < n; i++) {
        while (bits <= 24) { buf |= (pos < end ? b[pos] : 0) << bits; pos++; bits += 8; }
        const e = lut[buf & (HUFF_SIZE - 1)];
        if (!e) bad();
        const l = e >> 8;
        buf >>>= l; bits -= l; used += l;
        out[o0 + Math.floor(i / tbw) * rowb + (i % tbw) * S + k] = e & 255;
      }
    }
    if (Math.ceil(used / 8) !== end - p) bad();
  }

  const BLOCK_FORMATS = {
    0x40: [4, 4, 8], 0x41: [4, 4, 16], 0x42: [4, 4, 16], 0x43: [4, 4, 8], 0x44: [4, 4, 8],
    0x45: [4, 4, 16], 0x46: [4, 4, 16], 0x47: [4, 4, 16], 0x48: [4, 4, 16], 0x49: [4, 4, 16],
    0x50: [4, 4, 8], 0x51: [4, 4, 8], 0x52: [4, 4, 16], 0x53: [4, 4, 8], 0x54: [4, 4, 8],
    0x55: [4, 4, 16], 0x56: [4, 4, 16]
  };
  [[4, 4], [5, 4], [5, 5], [6, 5], [6, 6], [8, 5], [8, 6], [8, 8], [10, 5], [10, 6], [10, 8],
   [10, 10], [12, 10], [12, 12]].forEach(([w, h], i) => { BLOCK_FORMATS[0x60 + i] = [w, h, 16]; });

  function mipSize(t, m) {
    return [Math.max(1, t.width >>> m), Math.max(1, t.height >>> m),
            t.shape === 2 ? Math.max(1, t.depth >>> m) : 1];
  }

  function surfaceBytes(t, m) {
    const [w, h, d] = mipSize(t, m);
    if (t.payload === 1) {
      const [bw, bh, S] = BLOCK_FORMATS[t.format];
      return Math.ceil(w / bw) * Math.ceil(h / bh) * d * S;
    }
    return w * h * d * t.channels * (t.sample === 0 ? 1 : t.sample === 3 ? 4 : 2);
  }

  /* Decodes one surface (v2) into a typed array. */
  function decodeSurface(b, t, s, verify) {
    const m = s % t.mipLevels, [w, h, d] = mipSize(t, m);
    const off = t._off[s], size = t._size[s], blocks = t.payload === 1;
    let tcx, tcy, nbx = 0, nby = 0, S = 0;
    if (blocks) {
      const f = BLOCK_FORMATS[t.format];
      nbx = Math.ceil(w / f[0]); nby = Math.ceil(h / f[1]); S = f[2];
      tcx = Math.ceil(nbx / BLOCK_TILE); tcy = Math.ceil(nby / BLOCK_TILE);
    } else {
      tcx = Math.ceil(w / TILE); tcy = Math.ceil(h / TILE);
    }
    const tiles = tcx * tcy * d;
    if (size < 4) bad();
    const bl = r32(b, off);
    if (bl > size - 4 || Math.floor((size - 4 - bl) / 8) < tiles) bad();
    const pre = 4 + bl;
    if (verify && checksum(b, off, pre + tiles * 8) !== t._tcheck[s]) fail('checksum', 'damaged file: a checksum does not match');
    let book = null;
    if (bl) {
      if (!(t.needs & NEED.ENTROPY)) bad();
      book = readBook(b, off + 4, bl);
    }
    const table = off + pre, end = off + size;
    let pos = table + tiles * 8;
    const sizes = new Array(tiles), packed = new Array(tiles), starts = new Array(tiles);
    for (let i = 0; i < tiles; i++) {
      let sz = r32(b, table + i * 8);
      packed[i] = sz >>> 31;
      sz &= 0x7FFFFFFF;
      if (packed[i] && (!blocks || !book)) bad();
      if (sz > end - pos) bad();
      starts[i] = pos; sizes[i] = sz; pos += sz;
    }
    if (pos !== end) bad();

    const bytes = surfaceBytes(t, m);
    let out, store;
    if (blocks || t.sample === 0) out = store = new Uint8Array(bytes);
    else if (t.sample === 3) { store = new Uint32Array(bytes / 4); out = new Float32Array(store.buffer); }
    else out = store = new Uint16Array(bytes / 2);
    for (let i = 0; i < tiles; i++) {
      const p = starts[i], e = p + sizes[i];
      if (verify && checksum(b, p, sizes[i]) !== r32(b, table + i * 8 + 4))
        fail('checksum', 'damaged file: a checksum does not match');
      const row = Math.floor(i / tcx), z = Math.floor(row / tcy), ty = row % tcy, tx = i % tcx;
      if (blocks) {
        const bx0 = tx * BLOCK_TILE, by0 = ty * BLOCK_TILE, rowb = nbx * S;
        decodeBlockTile(b, p, e, packed[i], store, z * nby * rowb + by0 * rowb + bx0 * S, rowb,
                        Math.min(BLOCK_TILE, nbx - bx0), Math.min(BLOCK_TILE, nby - by0), S, book);
      } else {
        const x0 = tx * TILE, y0 = ty * TILE, tw = Math.min(TILE, w - x0), th = Math.min(TILE, h - y0);
        const slice = w * h * t.channels;
        const view = store.subarray(z * slice, (z + 1) * slice);
        if (t.sample === 0) decodeTile(b, p, e, view, w, x0, y0, tw, th, t.channels, true, book);
        else decodeTileWide(b, p, e, view, w, x0, y0, tw, th, t.channels, t.sample, book);
      }
    }
    return out;
  }

  /*
   * decodeTexture(bytes, { verify = true }) — any YAPF file (v1 or v2).
   * Returns { version, width, height, depth, layers, frames, faces, shape,
   * mipLevels, payload, format, sample, channels, flags, channelMap,
   * linearMask, normal, primaries, transfer, mipFilter, alphaRef,
   * loopCount, frameUs, notes: [{ tag, data }], surfaces: [...] }, where
   * surfaces[s] is a Uint8Array (8-bit pixels, GPU blocks), Uint16Array
   * (16-bit, half bits) or Float32Array, numbered
   * s = ((frame · layers + layer) · faces + face) · mipLevels + mip.
   * Errors are YapfError with .code 'not-yapf', 'version', 'unsupported',
   * 'corrupt', 'checksum' or 'truncated'.
   */
  function decodeTexture(input, opts) {
    const b = input instanceof Uint8Array ? input : new Uint8Array(input);
    const verify = !(opts && opts.verify === false);
    if (b.length < 5 || b[0] !== 0x59 || b[1] !== 0x41 || b[2] !== 0x50 || b[3] !== 0x46)
      fail('not-yapf', 'not a YAPF file');
    if (b[4] === 1) {
      const img = decodeV1(b);
      return { version: 1, width: img.width, height: img.height, depth: 1, layers: 1, frames: 1,
               faces: 1, shape: 0, mipLevels: img.mipLevels, payload: 0, format: img.gpuFormat,
               sample: 0, channels: img.channels, flags: img.flags, channelMap: [0, 0, 0, 0],
               linearMask: 0, normal: 0, primaries: 0, transfer: 0, mipFilter: 0, alphaRef: 0,
               loopCount: 0, frameUs: [], notes: [], surfaces: img.mips };
    }
    if (b[4] !== 2) fail('version', 'format version ' + b[4] + ' is newer than this decoder');
    if (b.length < 64) fail('truncated', 'the file is truncated');
    if (verify && checksum(b, 0, 0x3C) !== r32(b, 0x3C)) fail('checksum', 'damaged file: a checksum does not match');
    const t = {
      version: 2, channels: b[5], format: b[6], mipLevels: b[7], flags: b[8], payload: b[9],
      sample: b[10], shape: b[11], width: r32(b, 0x0C), height: r32(b, 0x10), depth: r32(b, 0x14),
      layers: r16(b, 0x18), frames: r16(b, 0x1A), needs: r32(b, 0x1C),
      channelMap: Array.from(b.subarray(0x20, 0x24)), linearMask: b[0x24], normal: b[0x25],
      primaries: b[0x26], transfer: b[0x27], mipFilter: b[0x28], alphaRef: b[0x29],
      loopCount: r16(b, 0x2A), frameUs: [], notes: []
    };
    const notesSize = r32(b, 0x2C), fileSize = r64(b, 0x30);
    if (t.needs & ~NEED.ALL) fail('unsupported', 'the file needs a feature this decoder does not have');
    t.faces = t.shape === 1 ? 6 : 1;
    if (t.channels < 1 || t.channels > 4 || t.sample > 3 || t.payload > 1 || t.shape > 2 ||
        t.width < 1 || t.width > MAX_DIM || t.height < 1 || t.height > MAX_DIM ||
        !t.layers || !t.frames || t.mipLevels < 1 || t.mipLevels > MAX_MIPS) bad();
    if (t.shape === 2 ? (t.depth < 1 || t.depth > MAX_DIM || t.layers !== 1) : t.depth > 1) bad();
    if (t.shape !== 2) t.depth = 1;
    if (t.shape === 1 && t.width !== t.height) bad();
    if (t.payload === 1 && !BLOCK_FORMATS[t.format]) bad();
    if ((t.payload === 0 && t.sample !== 0 && !(t.needs & NEED.WIDE)) ||
        (t.payload === 1 && !(t.needs & NEED.BLOCKS)) ||
        ((t.shape !== 0 || t.layers > 1) && !(t.needs & NEED.LAYOUT)) ||
        (t.frames > 1 && !(t.needs & NEED.FRAMES))) bad();
    const S = t.frames * t.layers * t.faces * t.mipLevels;
    if (S > (1 << 24)) bad();
    const front = 64 + 16 * S + (t.frames > 1 ? 4 * t.frames : 0) + notesSize;
    if (front > fileSize) bad();
    if (b.length < fileSize) fail('truncated', 'the file is truncated');
    if (verify && checksum(b, 64, front - 64) !== r32(b, 0x38)) fail('checksum', 'damaged file: a checksum does not match');
    let q = 64 + 16 * S;
    for (let f = 0; t.frames > 1 && f < t.frames; f++, q += 4) t.frameUs.push(r32(b, q));
    const qe = q + notesSize;
    while (q < qe) {
      if (qe - q < 8) bad();
      const sz = r32(b, q + 4);
      if (qe - q - 8 < sz) bad();
      t.notes.push({ tag: String.fromCharCode(b[q], b[q + 1], b[q + 2], b[q + 3]), data: b.slice(q + 8, q + 8 + sz) });
      q += 8 + sz;
    }
    t._off = []; t._size = []; t._tcheck = [];
    for (let s = 0; s < S; s++) {
      const e = 64 + 16 * s, off = r64(b, e), size = r32(b, e + 8);
      if (off < front || off > fileSize || size > fileSize - off) bad();
      t._off.push(off); t._size.push(size); t._tcheck.push(r32(b, e + 12));
    }
    t.surfaces = [];
    for (let s = 0; s < S; s++) t.surfaces.push(decodeSurface(b, t, s, verify));
    delete t._off; delete t._size; delete t._tcheck;
    return t;
  }

  /* ── GPU block decoding (previews) ───────────────────────────────── */

  const PART2 = [0xCCCC, 0x8888, 0xEEEE, 0xECC8, 0xC880, 0xFEEC, 0xFEC8, 0xEC80, 0xC800, 0xFFEC, 0xFE80, 0xE800,
    0xFFE8, 0xFF00, 0xFFF0, 0xF000, 0xF710, 0x008E, 0x7100, 0x08CE, 0x008C, 0x7310, 0x3100, 0x8CCE, 0x088C, 0x3110,
    0x6666, 0x366C, 0x17E8, 0x0FF0, 0x718E, 0x399C, 0xAAAA, 0xF0F0, 0x5A5A, 0x33CC, 0x3C3C, 0x55AA, 0x9696, 0xA55A,
    0x73CE, 0x13C8, 0x324C, 0x3BDC, 0x6996, 0xC33C, 0x9966, 0x0660, 0x0272, 0x04E4, 0x4E40, 0x2720, 0xC936, 0x936C,
    0x39C6, 0x639C, 0x9336, 0x9CC6, 0x817E, 0xE718, 0xCCF0, 0x0FCC, 0x7744, 0xEE22];
  const PART3 = [0xAA685050, 0x6A5A5040, 0x5A5A4200, 0x5450A0A8, 0xA5A50000, 0xA0A05050, 0x5555A0A0, 0x5A5A5050,
    0xAA550000, 0xAA555500, 0xAAAA5500, 0x90909090, 0x94949494, 0xA4A4A4A4, 0xA9A59450, 0x2A0A4250, 0xA5945040,
    0x0A425054, 0xA5A5A500, 0x55A0A0A0, 0xA8A85454, 0x6A6A4040, 0xA4A45000, 0x1A1A0500, 0x0050A4A4, 0xAAA59090,
    0x14696914, 0x69691400, 0xA08585A0, 0xAA821414, 0x50A4A450, 0x6A5A0200, 0xA9A58000, 0x5090A0A8, 0xA8A09050,
    0x24242424, 0x00AA5500, 0x24924924, 0x24499224, 0x50A50A50, 0x500AA550, 0xAAAA4444, 0x66660000, 0xA5A0A5A0,
    0x50A050A0, 0x69286928, 0x44AAAA44, 0x66666600, 0xAA444444, 0x54A854A8, 0x95809580, 0x96969600, 0xA85454A8,
    0x80959580, 0xAA141414, 0x96960000, 0xAAAA1414, 0xA05050A0, 0xA0A5A5A0, 0x96000000, 0x40804080, 0xA9A8A9A8,
    0xAAAAAA44, 0x2A4A5254];
  const ANCHOR2 = [15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 2, 8, 2, 2, 8, 8, 15, 2, 8, 2, 2,
    8, 8, 2, 2, 15, 15, 6, 8, 2, 8, 15, 15, 2, 8, 2, 2, 2, 15, 15, 6, 6, 2, 6, 8, 15, 15, 2, 2, 15, 15, 15, 15, 15, 2, 2, 15];
  const ANCHOR3A = [3, 3, 15, 15, 8, 3, 15, 15, 8, 8, 6, 6, 6, 5, 3, 3, 3, 3, 8, 15, 3, 3, 6, 10, 5, 8, 8, 6, 8, 5, 15,
    15, 8, 15, 3, 5, 6, 10, 8, 15, 15, 3, 15, 5, 15, 15, 15, 15, 3, 15, 5, 5, 5, 8, 5, 10, 5, 10, 8, 13, 15, 12, 3, 3];
  const ANCHOR3B = [15, 8, 8, 3, 15, 15, 3, 8, 15, 15, 15, 15, 15, 15, 15, 8, 15, 8, 15, 3, 15, 8, 15, 8, 3, 15, 6, 10,
    15, 15, 10, 8, 15, 3, 15, 10, 10, 8, 9, 10, 6, 15, 8, 15, 3, 6, 6, 8, 15, 3, 15, 15, 15, 15, 15, 15, 15, 15, 15,
    15, 3, 15, 15, 8];
  const WEIGHTS = { 2: [0, 21, 43, 64], 3: [0, 9, 18, 27, 37, 46, 55, 64],
                    4: [0, 4, 9, 13, 17, 21, 26, 30, 34, 38, 43, 47, 51, 55, 60, 64] };
  const interp = (a, b, w) => (a * (64 - w) + b * w + 32) >> 6;

  function bits128(b, o) {
    let pos = 0;
    return (n) => {
      let v = 0;
      for (let i = 0; i < n; i++, pos++) v |= ((b[o + (pos >> 3)] >> (pos & 7)) & 1) << i;
      return v >>> 0;
    };
  }

  function rgb565(c) {
    const r = (c >> 11) & 31, g = (c >> 5) & 63, bl = c & 31;
    return [(r << 3) | (r >> 2), (g << 2) | (g >> 4), (bl << 3) | (bl >> 2)];
  }

  function bc1Block(b, o, out, fourOnly) {
    const c0 = r16(b, o), c1 = r16(b, o + 2), idx = r32(b, o + 4), four = c0 > c1 || fourOnly;
    const p0 = rgb565(c0), p1 = rgb565(c1), pal = [p0.concat(255), p1.concat(255), [0, 0, 0, 255], [0, 0, 0, 255]];
    for (let k = 0; k < 3; k++) {
      if (four) { pal[2][k] = ((2 * p0[k] + p1[k] + 1) / 3) | 0; pal[3][k] = ((p0[k] + 2 * p1[k] + 1) / 3) | 0; }
      else { pal[2][k] = (p0[k] + p1[k] + 1) >> 1; pal[3][k] = 0; }
    }
    if (!four) pal[3][3] = 0;
    for (let i = 0; i < 16; i++) { const c = pal[(idx >>> (2 * i)) & 3]; for (let k = 0; k < 4; k++) out[i * 4 + k] = c[k]; }
  }

  function bc4Block(b, o, out, ch, snorm) {
    const pal = new Array(8);
    let r0 = b[o], r1 = b[o + 1];
    if (snorm) { r0 = Math.max(-127, (r0 << 24) >> 24); r1 = Math.max(-127, (r1 << 24) >> 24); }
    pal[0] = r0; pal[1] = r1;
    const div = (v, d) => (v >= 0 ? Math.floor((v + (d >> 1)) / d) : -Math.floor((-v + (d >> 1)) / d));
    if (r0 > r1) for (let i = 2; i < 8; i++) pal[i] = div((8 - i) * r0 + (i - 1) * r1, 7);
    else { for (let i = 2; i < 6; i++) pal[i] = div((6 - i) * r0 + (i - 1) * r1, 5); pal[6] = snorm ? -127 : 0; pal[7] = snorm ? 127 : 255; }
    let lo = r32(b, o + 2), hi = r16(b, o + 6);
    for (let i = 0; i < 16; i++) {
      const bit = 3 * i, v = bit < 30 ? (lo >>> bit) & 7 : bit === 30 ? ((lo >>> 30) | ((hi & 1) << 2)) : (hi >> (bit - 32)) & 7;
      out[i * 4 + ch] = pal[v] + (snorm ? 128 : 0);
    }
  }

  const BC7 = [[3, 4, 0, 0, 4, 0, 1, 0, 3, 0], [2, 6, 0, 0, 6, 0, 0, 1, 3, 0], [3, 6, 0, 0, 5, 0, 0, 0, 2, 0],
    [2, 6, 0, 0, 7, 0, 1, 0, 2, 0], [1, 0, 2, 1, 5, 6, 0, 0, 2, 3], [1, 0, 2, 0, 7, 8, 0, 0, 2, 2],
    [1, 0, 0, 0, 7, 7, 1, 0, 4, 0], [2, 6, 0, 0, 5, 5, 1, 0, 2, 0]];
  const subsetOf = (ns, part, i) => ns === 2 ? (PART2[part] >> i) & 1 : ns === 3 ? (PART3[part] >>> (2 * i)) & 3 : 0;
  const isAnchor = (ns, part, i) => i === 0 || (ns === 2 && i === ANCHOR2[part]) ||
    (ns === 3 && (i === ANCHOR3A[part] || i === ANCHOR3B[part]));

  function bc7Block(b, o, out) {
    const get = bits128(b, o);
    let mode = 0;
    while (mode < 8 && !get(1)) mode++;
    if (mode === 8) { out.fill(0, 0, 64); return; }
    const [ns, pb, rb, isbB, cb, ab, epb, spb, ib, ib2] = BC7[mode];
    const part = get(pb), rot = get(rb), isb = get(isbB), ne = ns * 2;
    const ep = []; for (let e = 0; e < ne; e++) ep.push([0, 0, 0, 255]);
    for (let c = 0; c < 3; c++) for (let e = 0; e < ne; e++) ep[e][c] = get(cb);
    for (let e = 0; e < ne; e++) ep[e][3] = ab ? get(ab) : 255;
    const pbit = epb | spb;
    if (epb) for (let e = 0; e < ne; e++) { const p = get(1); for (let c = 0; c < 4; c++) if (c < 3 || ab) ep[e][c] = (ep[e][c] << 1) | p; }
    else if (spb) for (let k = 0; k < ns; k++) { const p = get(1); for (let c = 0; c < 3; c++) { ep[2 * k][c] = (ep[2 * k][c] << 1) | p; ep[2 * k + 1][c] = (ep[2 * k + 1][c] << 1) | p; } }
    for (let e = 0; e < ne; e++) for (let c = 0; c < 4; c++) {
      if (c === 3 && !ab) continue;
      const nb = (c < 3 ? cb : ab) + pbit, v = ep[e][c] << (8 - nb);
      ep[e][c] = v | (v >> nb);
    }
    const idx = [], idx2 = [];
    for (let i = 0; i < 16; i++) idx.push(get(ib - (isAnchor(ns, part, i) ? 1 : 0)));
    for (let i = 0; i < 16; i++) idx2.push(ib2 ? get(ib2 - (i === 0 ? 1 : 0)) : 0);
    const w1 = WEIGHTS[ib], w2 = WEIGHTS[ib2 || 2];
    for (let i = 0; i < 16; i++) {
      const k = subsetOf(ns, part, i), A = ep[2 * k], B = ep[2 * k + 1];
      let cw, aw;
      if (!ib2) cw = aw = w1[idx[i]];
      else if (!isb) { cw = w1[idx[i]]; aw = w2[idx2[i]]; }
      else { cw = w2[idx2[i]]; aw = w1[idx[i]]; }
      const px = [interp(A[0], B[0], cw), interp(A[1], B[1], cw), interp(A[2], B[2], cw), interp(A[3], B[3], aw)];
      if (rot) { const t = px[3]; px[3] = px[rot - 1]; px[rot - 1] = t; }
      for (let c = 0; c < 4; c++) out[i * 4 + c] = px[c];
    }
  }

  /* BC6H header layouts: [field, first bit, count]; fields 0–3 red w x y z,
   * 4–7 green, 8–11 blue, 12 partition. */
  const RW = 0, RX = 1, RY = 2, RZ = 3, GW = 4, GX = 5, GY = 6, GZ = 7, BW = 8, BX = 9, BY = 10, BZ = 11, PD = 12;
  const BC6 = [
    [0x00, 10, 5, 5, 5, [[GY,4,1],[BY,4,1],[BZ,4,1],[RW,0,10],[GW,0,10],[BW,0,10],[RX,0,5],[GZ,4,1],[GY,0,4],[GX,0,5],[BZ,0,1],[GZ,0,4],[BX,0,5],[BZ,1,1],[BY,0,4],[RY,0,5],[BZ,2,1],[RZ,0,5],[BZ,3,1],[PD,0,5]]],
    [0x01, 7, 6, 6, 6, [[GY,5,1],[GZ,4,1],[GZ,5,1],[RW,0,7],[BZ,0,1],[BZ,1,1],[BY,4,1],[GW,0,7],[BY,5,1],[BZ,2,1],[GY,4,1],[BW,0,7],[BZ,3,1],[BZ,5,1],[BZ,4,1],[RX,0,6],[GY,0,4],[GX,0,6],[GZ,0,4],[BX,0,6],[BY,0,4],[RY,0,6],[RZ,0,6],[PD,0,5]]],
    [0x02, 11, 5, 4, 4, [[RW,0,10],[GW,0,10],[BW,0,10],[RX,0,5],[RW,10,1],[GY,0,4],[GX,0,4],[GW,10,1],[BZ,0,1],[GZ,0,4],[BX,0,4],[BW,10,1],[BZ,1,1],[BY,0,4],[RY,0,5],[BZ,2,1],[RZ,0,5],[BZ,3,1],[PD,0,5]]],
    [0x06, 11, 4, 5, 4, [[RW,0,10],[GW,0,10],[BW,0,10],[RX,0,4],[RW,10,1],[GZ,4,1],[GY,0,4],[GX,0,5],[GW,10,1],[GZ,0,4],[BX,0,4],[BW,10,1],[BZ,1,1],[BY,0,4],[RY,0,4],[BZ,0,1],[BZ,2,1],[RZ,0,4],[GY,4,1],[BZ,3,1],[PD,0,5]]],
    [0x0A, 11, 4, 4, 5, [[RW,0,10],[GW,0,10],[BW,0,10],[RX,0,4],[RW,10,1],[BY,4,1],[GY,0,4],[GX,0,4],[GW,10,1],[BZ,0,1],[GZ,0,4],[BX,0,5],[BW,10,1],[BY,0,4],[RY,0,4],[BZ,1,1],[BZ,2,1],[RZ,0,4],[BZ,4,1],[BZ,3,1],[PD,0,5]]],
    [0x0E, 9, 5, 5, 5, [[RW,0,9],[BY,4,1],[GW,0,9],[GY,4,1],[BW,0,9],[BZ,4,1],[RX,0,5],[GZ,4,1],[GY,0,4],[GX,0,5],[BZ,0,1],[GZ,0,4],[BX,0,5],[BZ,1,1],[BY,0,4],[RY,0,5],[BZ,2,1],[RZ,0,5],[BZ,3,1],[PD,0,5]]],
    [0x12, 8, 6, 5, 5, [[RW,0,8],[GZ,4,1],[BY,4,1],[GW,0,8],[BZ,2,1],[GY,4,1],[BW,0,8],[BZ,3,1],[BZ,4,1],[RX,0,6],[GY,0,4],[GX,0,5],[BZ,0,1],[GZ,0,4],[BX,0,5],[BZ,1,1],[BY,0,4],[RY,0,6],[RZ,0,6],[PD,0,5]]],
    [0x16, 8, 5, 6, 5, [[RW,0,8],[BZ,0,1],[BY,4,1],[GW,0,8],[GY,5,1],[GY,4,1],[BW,0,8],[GZ,5,1],[BZ,4,1],[RX,0,5],[GZ,4,1],[GY,0,4],[GX,0,6],[GZ,0,4],[BX,0,5],[BZ,1,1],[BY,0,4],[RY,0,5],[BZ,2,1],[RZ,0,5],[BZ,3,1],[PD,0,5]]],
    [0x1A, 8, 5, 5, 6, [[RW,0,8],[BZ,1,1],[BY,4,1],[GW,0,8],[BY,5,1],[GY,4,1],[BW,0,8],[BZ,5,1],[BZ,4,1],[RX,0,5],[GZ,4,1],[GY,0,4],[GX,0,5],[BZ,0,1],[GZ,0,4],[BX,0,6],[BY,0,4],[RY,0,5],[BZ,2,1],[RZ,0,5],[BZ,3,1],[PD,0,5]]],
    [0x1E, 6, 6, 6, 6, [[RW,0,6],[GZ,4,1],[BZ,0,1],[BZ,1,1],[BY,4,1],[GW,0,6],[GY,5,1],[BY,5,1],[BZ,2,1],[GY,4,1],[BW,0,6],[GZ,5,1],[BZ,3,1],[BZ,5,1],[BZ,4,1],[RX,0,6],[GY,0,4],[GX,0,6],[GZ,0,4],[BX,0,6],[BY,0,4],[RY,0,6],[RZ,0,6],[PD,0,5]]],
    [0x03, 10, 10, 10, 10, [[RW,0,10],[GW,0,10],[BW,0,10],[RX,0,10],[GX,0,10],[BX,0,10]]],
    [0x07, 11, 9, 9, 9, [[RW,0,10],[GW,0,10],[BW,0,10],[RX,0,9],[RW,10,1],[GX,0,9],[GW,10,1],[BX,0,9],[BW,10,1]]],
    [0x0B, 12, 8, 8, 8, [[RW,0,10],[GW,0,10],[BW,0,10],[RX,0,8],[RW,11,1],[RW,10,1],[GX,0,8],[GW,11,1],[GW,10,1],[BX,0,8],[BW,11,1],[BW,10,1]]],
    [0x0F, 16, 4, 4, 4, [[RW,0,10],[GW,0,10],[BW,0,10],[RX,0,4],[RW,15,1],[RW,14,1],[RW,13,1],[RW,12,1],[RW,11,1],[RW,10,1],[GX,0,4],[GW,15,1],[GW,14,1],[GW,13,1],[GW,12,1],[GW,11,1],[GW,10,1],[BX,0,4],[BW,15,1],[BW,14,1],[BW,13,1],[BW,12,1],[BW,11,1],[BW,10,1]]]
  ];
  const sext = (v, n) => { const m = 1 << (n - 1); v &= (1 << n) - 1; return (v ^ m) - m; };
  function bc6Unq(v, n, sgn) {
    if (!sgn) {
      if (n >= 15) return v;
      if (v === 0) return 0;
      if (v === (1 << n) - 1) return 0xFFFF;
      return ((v << 16) + 0x8000) >> n;
    }
    if (n >= 16) return v;
    const s = v < 0; if (s) v = -v;
    const u = v === 0 ? 0 : v >= (1 << (n - 1)) - 1 ? 0x7FFF : ((v << 15) + 0x4000) >> (n - 1);
    return s ? -u : u;
  }
  function bc6Finish(v, sgn) {
    if (!sgn) return (v * 31) >> 6;
    v = v < 0 ? -(((-v) * 31) >> 5) : (v * 31) >> 5;
    return v < 0 ? 0x8000 | -v : v;
  }
  function bc6Block(b, o, out, sgn) {
    const get = bits128(b, o);
    let code = get(2);
    if (code > 1) code |= get(3) << 2;
    const m = BC6.findIndex((x) => x[0] === code);
    if (m < 0) { out.fill(0, 0, 48); return; }
    const [, W, dr, dg, db, seg] = BC6[m], f = new Array(13).fill(0);
    for (const [fi, lo, n] of seg) f[fi] |= get(n) << lo;
    const regions = m < 10 ? 2 : 1, ne = regions * 2, dbits = [dr, dg, db], ep = [[], [], [], []];
    for (let c = 0; c < 3; c++) {
      for (let e = 0; e < ne; e++) ep[e][c] = f[c * 4 + e];
      if (sgn) ep[0][c] = sext(ep[0][c], W);
      const delta = m !== 9 && m !== 10;
      for (let e = 1; e < ne; e++) {
        if (delta || sgn) ep[e][c] = sext(ep[e][c], dbits[c]);
        if (delta) { ep[e][c] = (ep[e][c] + ep[0][c]) & ((1 << W) - 1); if (sgn) ep[e][c] = sext(ep[e][c], W); }
      }
      for (let e = 0; e < ne; e++) ep[e][c] = bc6Unq(ep[e][c], W, sgn);
    }
    const part = f[PD], ib = regions === 2 ? 3 : 4, wt = WEIGHTS[ib];
    for (let i = 0; i < 16; i++) {
      const k = regions === 2 ? (PART2[part] >> i) & 1 : 0;
      const anchor = i === 0 || (regions === 2 && i === ANCHOR2[part]);
      const ix = get(ib - (anchor ? 1 : 0));
      for (let c = 0; c < 3; c++) out[i * 3 + c] = bc6Finish(interp(ep[2 * k][c], ep[2 * k + 1][c], wt[ix]), sgn);
    }
  }

  /* decodeBlocks(format, blocks, w, h) → RGBA Uint8Array (LDR) or RGB
   * half-bits Uint16Array (BC6H); null for ETC2 / EAC / ASTC. */
  function decodeBlocks(format, blocks, w, h) {
    if (format >= 0x50 || !BLOCK_FORMATS[format]) return null;
    const S = BLOCK_FORMATS[format][2], nbx = Math.ceil(w / 4), nby = Math.ceil(h / 4);
    const hdr = format === 0x47 || format === 0x48;
    const out = hdr ? new Uint16Array(w * h * 3) : new Uint8Array(w * h * 4);
    const px = new Int32Array(64), hx = new Int32Array(48);
    let o = 0;
    for (let by = 0; by < nby; by++)
      for (let bx = 0; bx < nbx; bx++, o += S) {
        switch (format) {
          case 0x40: bc1Block(blocks, o, px, false); break;
          case 0x41:
            bc1Block(blocks, o + 8, px, true);
            for (let i = 0; i < 16; i++) px[i * 4 + 3] = ((blocks[o + (i >> 1)] >> (4 * (i & 1))) & 15) * 17;
            break;
          case 0x42: bc1Block(blocks, o + 8, px, true); bc4Block(blocks, o, px, 3, false); break;
          case 0x43: case 0x44:
            px.fill(0); bc4Block(blocks, o, px, 0, format === 0x44);
            for (let i = 0; i < 16; i++) px[i * 4 + 3] = 255;
            break;
          case 0x45: case 0x46:
            px.fill(0); bc4Block(blocks, o, px, 0, format === 0x46); bc4Block(blocks, o + 8, px, 1, format === 0x46);
            for (let i = 0; i < 16; i++) px[i * 4 + 3] = 255;
            break;
          case 0x49: bc7Block(blocks, o, px); break;
          default: bc6Block(blocks, o, hx, format === 0x48);
        }
        for (let y = 0; y < 4 && by * 4 + y < h; y++)
          for (let x = 0; x < 4 && bx * 4 + x < w; x++) {
            const d = (by * 4 + y) * w + bx * 4 + x, i = y * 4 + x;
            if (hdr) for (let c = 0; c < 3; c++) out[d * 3 + c] = hx[i * 3 + c];
            else for (let c = 0; c < 4; c++) out[d * 4 + c] = px[i * 4 + c];
          }
      }
    return out;
  }

  function halfToFloat(h) {
    const s = h & 0x8000 ? -1 : 1, e = (h >> 10) & 31, m = h & 0x3FF;
    if (e === 0) return s * m * Math.pow(2, -24);
    if (e === 31) return m ? NaN : s * Infinity;
    return s * (1 + m / 1024) * Math.pow(2, e - 15);
  }

  const linToSrgb = (v) => !(v > 0) ? 0 : v >= 1 ? 255
    : Math.round(255 * (v <= 0.0031308 ? v * 12.92 : 1.055 * Math.pow(v, 1 / 2.4) - 0.055));

  /*
   * textureToRGBA(tex, surface = 0, slice = 0) → { width, height,
   * rgba: Uint8ClampedArray } for display: gray expanded, 16-bit rounded,
   * half / float clamped and sRGB encoded, GPU blocks decoded.  Throws for
   * ETC2 / EAC / ASTC.
   */
  function textureToRGBA(tex, surface, slice) {
    surface = surface || 0; slice = slice || 0;
    const m = surface % tex.mipLevels, [w, h, d] = mipSize(tex, m), n = w * h;
    const data = tex.surfaces[surface], rgba = new Uint8ClampedArray(n * 4);
    let src, ch = tex.channels, kind = tex.payload === 1 ? 'u8' : ['u8', 'u16', 'f16', 'f32'][tex.sample];
    if (tex.payload === 1) {
      const per = data.length / d, blk = decodeBlocks(tex.format, data.subarray(per * slice, per * (slice + 1)), w, h);
      if (!blk) fail('unsupported', 'ETC2 / EAC / ASTC blocks cannot be shown');
      if (blk instanceof Uint16Array) { src = blk; ch = 3; kind = 'f16'; }
      else {
        rgba.set(blk);
        if (tex.channels === 3) for (let i = 0; i < n; i++) rgba[i * 4 + 3] = 255;
        return { width: w, height: h, rgba };
      }
    } else {
      src = data.subarray(n * ch * slice, n * ch * (slice + 1));
    }
    for (let i = 0; i < n; i++) {
      const v = [0, 0, 0, 255];
      for (let c = 0; c < ch; c++) {
        const x = src[i * ch + c], alpha = (ch === 2 && c === 1) || (ch === 4 && c === 3);
        let q;
        if (kind === 'u8') q = x;
        else if (kind === 'u16') q = Math.round(x / 257);
        else {
          const f = kind === 'f16' ? halfToFloat(x) : x;
          q = alpha ? Math.max(0, Math.min(255, Math.round(f * 255))) : linToSrgb(f);
        }
        v[ch <= 2 ? (c === 0 ? 0 : 3) : c] = q;
      }
      if (ch <= 2) v[1] = v[2] = v[0];
      rgba.set(v, i * 4);
    }
    return { width: w, height: h, rgba };
  }

  function surfaceIndex(tex, frame, layer, face, mip) {
    return (((frame || 0) * tex.layers + (layer || 0)) * tex.faces + (face || 0)) * tex.mipLevels + (mip || 0);
  }

  /* ── Decoder ──────────────────────────────────────────────────────── */

  function unpackPlane(b, p, end, z, tw, th) {
    const total = tw * th, ng = (total + GROUP - 1) >> 3, nb = (th + BAND - 1) >> 3;
    if (end - p < nb) corrupt();
    const filt = b.subarray(p, p + nb);
    p += nb;
    for (let i = 0; i < nb; i++) if (!filterValid(filt[i])) corrupt();

    const gw = new Uint8Array(ng + 64);
    let data = 0, g = 0, hi = 0, w = 0;
    while (g < ng) {
      if (p >= end) corrupt();
      const c = (b[p] >> (hi * 4)) & 15, n = NIB_GROUPS[c];
      p += hi; hi ^= 1;
      if (c < NIB_REPEAT) w = c;
      gw.fill(w, g, g + n);
      data += w * n; g += n;
    }
    if (g !== ng) corrupt();
    if (hi) { if (b[p] >> 4) corrupt(); p++; }
    if (end - p < data) corrupt();

    for (g = 0; g < ng; g++) {
      w = gw[g];
      const o = g * GROUP, mask = (1 << w) - 1;
      let acc = 0, bits = 0;
      for (let i = 0; i < GROUP; i++) {
        while (bits < w) { acc |= b[p++] << bits; bits += 8; }
        z[o + i] = acc & mask;
        acc >>>= w; bits -= w;
      }
    }
    return { p, filt };
  }

  function unfilterRow(f, R, r0, U, u0, K, k0, Z, z0, tw) {
    if (f === F_LEFT) {
      let L = 0;
      for (let x = 0; x < tw; x++) R[r0 + x] = L = (L + unzz(Z[z0 + x])) & 255;
    } else if (f === F_GRAD) {
      let L = (U[u0] + unzz(Z[z0])) & 255;
      R[r0] = L;
      for (let x = 1; x < tw; x++)
        R[r0 + x] = L = (L + U[u0 + x] - U[u0 + x - 1] + unzz(Z[z0 + x])) & 255;
    } else {
      /* pred = (a + b) >> 1: Up k a = b = K;  Up-right a = b = U + 1;
       * Up-average a = U, b = U + 1.  Rows carry one extra sample. */
      let A, a0, B, b0;
      if (f >= F_UP) { A = K; a0 = k0; B = K; b0 = k0; }
      else if (f === F_UPAVG) { A = U; a0 = u0; B = U; b0 = u0 + 1; }
      else { A = U; a0 = u0 + 1; B = U; b0 = u0 + 1; }
      for (let x = 0; x < tw; x++)
        R[r0 + x] = (((A[a0 + x] + B[b0 + x]) >> 1) + unzz(Z[z0 + x])) & 255;
    }
    R[r0 + tw] = R[r0 + tw - 1];
  }

  function decodeTile(b, p, end, out, imgW, tx, ty, tw, th, ch, v2, book) {
    if (end <= p) corrupt();
    let hdr = b[p++];
    if (hdr === STORED) {
      const rowb = tw * ch;
      if (end - p !== rowb * th) corrupt();
      for (let y = 0; y < th; y++)
        out.set(b.subarray(p + rowb * y, p + rowb * (y + 1)), ((ty + y) * imgW + tx) * ch);
      return;
    }
    if (hdr & (v2 ? 0x80 : 0xE0)) corrupt();           /* reserved bits set */
    if ((hdr & 0x40) && (hdr & SUBGREEN)) corrupt();
    /* xf: 0 YCoCg-R, 1 subtract-green, 2 none (v2) */
    const xf = (hdr & 0x40) ? 2 : (hdr & SUBGREEN) ? 1 : 0, ent = hdr & 0x20;
    hdr &= 0x0F;
    if ((hdr >> ch) || (xf && ch < 3)) corrupt();
    let emask = 0;
    if (ent) {                                         /* v2: entropy planes */
      if (p >= end || !book) corrupt();
      emask = b[p++];
      if ((emask >> ch) || (emask & hdr)) corrupt();
    }

    const rowLen = TILE + 1, planeLen = RING * rowLen;
    const rows = new Uint8Array(4 * planeLen);
    const z = [], filt = [null, null, null, null];
    for (let c = 0; c < ch; c++) {
      if (!(hdr & (1 << c))) continue;
      if (p >= end) corrupt();
      rows.fill(b[p++], c * planeLen, (c + 1) * planeLen);
    }
    for (let c = 0; c < ch; c++) {
      if (hdr & (1 << c)) continue;
      z[c] = new Uint8Array(TILE_PX + GROUP);
      const r = (emask & (1 << c)) ? huffPlane(b, p, end, z[c], tw, th, book, xf * 16 + c)
                                   : unpackPlane(b, p, end, z[c], tw, th);
      p = r.p; filt[c] = r.filt;
    }
    if (p !== end) corrupt();

    for (let y = 0; y < th; y++) {
      const ri = (y % RING) * rowLen;
      for (let c = 0; c < ch; c++) {
        if (!filt[c]) continue;
        const f = filt[c][y >> 3], k = upK(f), base = c * planeLen;
        unfilterRow(f, rows, base + ri,
                    y ? rows : ZERO_ROW, y ? base + ((y - 1) % RING) * rowLen : 0,
                    y >= k ? rows : ZERO_ROW, y >= k ? base + ((y - k) % RING) * rowLen : 0,
                    z[c], y * tw, tw);
      }
      let d = ((ty + y) * imgW + tx) * ch;
      const P0 = ri, P1 = planeLen + ri, P2 = 2 * planeLen + ri, P3 = 3 * planeLen + ri;
      for (let x = 0; x < tw; x++, d += ch) {
        if (ch >= 3) {
          if (xf === 2) {
            out[d] = rows[P0 + x];
            out[d + 1] = rows[P1 + x];
            out[d + 2] = rows[P2 + x];
          } else if (xf) {
            const g = rows[P0 + x];
            out[d] = rows[P1 + x] + g - 128;
            out[d + 1] = g;
            out[d + 2] = rows[P2 + x] + g - 128;
          } else {
            const co = (rows[P1 + x] - 128) & 255, cg = (rows[P2 + x] - 128) & 255;
            const t = (rows[P0 + x] - (s8(cg) >> 1)) & 255;
            const bb = (t - (s8(co) >> 1)) & 255;
            out[d] = bb + co;
            out[d + 1] = cg + t;
            out[d + 2] = bb;
          }
          if (ch === 4) out[d + 3] = rows[P3 + x];
        } else {
          out[d] = rows[P0 + x];
          if (ch === 2) out[d + 1] = rows[P1 + x];
        }
      }
    }
  }

  const r32 = (b, p) => (b[p] | (b[p + 1] << 8) | (b[p + 2] << 16) | (b[p + 3] << 24)) >>> 0;

  /* decode(bytes) → 8-bit image.  Reads version 1, and version 2 files
   * that hold 8-bit pixels (2D; cube face 0 / layer 0 / frame 0).  Other
   * textures: see decodeTexture. */
  function decode(input) {
    const b = input instanceof Uint8Array ? input : new Uint8Array(input);
    if (b.length >= 5 && b[0] === 0x59 && b[1] === 0x41 && b[2] === 0x50 && b[3] === 0x46 && b[4] === 2) {
      const t = decodeTexture(b);
      if (t.payload !== 0 || t.sample !== 0 || t.shape === 2)
        throw new YapfError('unsupported', 'this is a YAPF 2 texture (GPU blocks, 16-bit / float or a ' +
                            'volume); use YAPF.decodeTexture and YAPF.textureToRGBA');
      const mips = t.surfaces.slice(0, t.mipLevels);
      return { width: t.width, height: t.height, channels: t.channels, gpuFormat: t.format,
               flags: t.flags, mipLevels: t.mipLevels, pixels: mips[0], mips };
    }
    return decodeV1(b);
  }

  function decodeV1(b) {
    if (b.length < 20 || b[0] !== 0x59 || b[1] !== 0x41 || b[2] !== 0x50 || b[3] !== 0x46)
      throw new YapfError('not-yapf', 'not a YAPF file');
    if (b[4] !== 1) throw new YapfError('version', 'unsupported format version ' + b[4]);
    const ch = b[5], mipLevels = b[7], W = r32(b, 12), H = r32(b, 16);
    if (ch < 1 || ch > 4 || mipLevels < 1 || mipLevels > MAX_MIPS ||
        W < 1 || W > MAX_DIM || H < 1 || H > MAX_DIM) corrupt();
    const idxEnd = 20 + 8 * mipLevels;
    if (b.length < idxEnd) corrupt();

    const mips = [];
    for (let m = 0; m < mipLevels; m++) {
      const off = r32(b, 20 + 8 * m), len = r32(b, 24 + 8 * m);
      const mw = Math.max(1, W >>> m), mh = Math.max(1, H >>> m);
      if (off < idxEnd || off > b.length || len > b.length - off) corrupt();
      const out = new Uint8Array(mw * mh * ch);
      const tcx = Math.ceil(mw / TILE), tcy = Math.ceil(mh / TILE), tcount = tcx * tcy;
      if (len / 4 < tcount) corrupt();
      let pos = off + tcount * 4;
      for (let t = 0; t < tcount; t++) {
        const sz = r32(b, off + t * 4);
        if (sz > off + len - pos) corrupt();
        const tx = (t % tcx) * TILE, ty = Math.floor(t / tcx) * TILE;
        decodeTile(b, pos, pos + sz, out, mw, tx, ty,
                   Math.min(TILE, mw - tx), Math.min(TILE, mh - ty), ch);
        pos += sz;
      }
      mips.push(out);
    }
    return { width: W, height: H, channels: ch, gpuFormat: b[6], flags: b[8],
             mipLevels, pixels: mips[0], mips };
  }

  /* ── Encoder ──────────────────────────────────────────────────────── */

  class Out {
    constructor(n) { this.buf = new Uint8Array(Math.max(n, 1024)); this.len = 0; }
    reserve(n) {
      if (this.len + n <= this.buf.length) return;
      let c = this.buf.length * 2;
      while (c < this.len + n) c *= 2;
      const nb = new Uint8Array(c); nb.set(this.buf.subarray(0, this.len)); this.buf = nb;
    }
    push(v) { this.reserve(1); this.buf[this.len++] = v; }
  }

  function predictRow(f, P, r0, u0, k0, pred, tw, U, K) {
    switch (f) {
      case F_LEFT: pred[0] = 0; for (let x = 1; x < tw; x++) pred[x] = P[r0 + x - 1]; break;
      case F_GRAD:
        pred[0] = U[u0];
        for (let x = 1; x < tw; x++) pred[x] = (P[r0 + x - 1] + U[u0 + x] - U[u0 + x - 1]) & 255;
        break;
      case F_UPRIGHT:
        for (let x = 0; x + 1 < tw; x++) pred[x] = U[u0 + x + 1];
        pred[tw - 1] = U[u0 + tw - 1];
        break;
      case F_UPAVG:
        for (let x = 0; x + 1 < tw; x++) pred[x] = (U[u0 + x] + U[u0 + x + 1]) >> 1;
        pred[tw - 1] = U[u0 + tw - 1];
        break;
      default: for (let x = 0; x < tw; x++) pred[x] = K[k0 + x];
    }
  }

  /* Picks a filter per band; fills z and filt; returns estimated cost. */
  function chooseFilters(P, tw, th, z, filt) {
    const total = tw * th, nb = (th + BAND - 1) >> 3;
    const tmp = new Uint8Array(BAND * TILE + GROUP), pred = new Uint8Array(TILE);
    let sum = 0, prevFi = 0;
    for (let b = 0; b < nb; b++) {
      const y0 = b * BAND, y1 = Math.min(y0 + BAND, th), n = (y1 - y0) * tw;
      let bestCost = Infinity, bestFi = 0;
      for (let t = 0; t < FILTERS.length; t++) {
        const fi = t === 0 ? prevFi : (t <= prevFi ? t - 1 : t);
        const f = FILTERS[fi], k = upK(f), serial = f === F_LEFT || f === F_GRAD;
        let cost = 0, done = 0, lost = false;
        for (let y = y0; y < y1 && !lost; y++) {
          const r0 = y * tw;
          const U = y ? P : ZERO_ROW, u0 = y ? r0 - tw : 0;
          const K = y >= k ? P : ZERO_ROW, k0 = y >= k ? r0 - k * tw : 0;
          predictRow(f, P, r0, u0, k0, pred, tw, U, K);
          const T = (y - y0) * tw;
          for (let x = 0; x < tw; x++) tmp[T + x] = zz((P[r0 + x] - pred[x]) & 255);
          const last = y + 1 === y1, end = last ? n : (y + 1 - y0) * tw;
          if (last) tmp.fill(0, n, n + GROUP);
          for (; done + GROUP <= end || (last && done < end); done += GROUP) {
            let m = 0;
            for (let i = 0; i < GROUP; i++) m |= tmp[done + i];
            const w = width(m);
            cost += w ? 16 * w + 8 : 2;
          }
          const c = serial ? cost + Math.floor(cost / 25) : cost;
          if (c > bestCost || (c === bestCost && fi > bestFi)) lost = true;
        }
        if (lost) continue;
        if (serial) cost += Math.floor(cost / 25);
        if (cost < bestCost || (cost === bestCost && fi < bestFi)) {
          bestCost = cost; bestFi = fi;
          z.set(tmp.subarray(0, n), y0 * tw);
        }
      }
      prevFi = bestFi;
      filt[b] = FILTERS[bestFi];
      sum += bestCost;
    }
    z.fill(0, total, total + GROUP);
    return sum;
  }

  function emitPlane(o, z, filt, tw, th) {
    const total = tw * th, ng = (total + GROUP - 1) >> 3, nb = (th + BAND - 1) >> 3;
    o.reserve(nb + ng + ng * 8);
    for (let i = 0; i < nb; i++) o.buf[o.len++] = filt[i];

    const need = new Uint8Array(ng);
    for (let g = 0; g < ng; g++) {
      let m = 0;
      for (let i = 0; i < GROUP; i++) m |= z[g * GROUP + i];
      need[g] = width(m);
    }
    /* span[j][g] = widest need in [g, g + 2^j) */
    const span = [need.slice()];
    for (let j = 1; j < 7; j++) {
      const prev = span[j - 1], cur = new Uint8Array(ng), h = 1 << (j - 1);
      for (let g = 0; g + (1 << j) <= ng; g++) cur[g] = Math.max(prev[g], prev[g + h]);
      span.push(cur);
    }
    const cost = new Uint32Array((ng + 1) * 9), pick = new Uint8Array(ng * 9);
    const mx = new Uint8Array(7);
    for (let g = ng - 1; g >= 0; g--) {
      let lc = Infinity, lk = 0;
      for (let w = need[g]; w <= 8; w++) {
        const c = 1 + 2 * w + cost[(g + 1) * 9 + w];
        if (c < lc) { lc = c; lk = w; }
      }
      let nl = 0;
      for (; nl < 7 && g + RUN_LENS[nl] <= ng; nl++) {
        const L = RUN_LENS[nl];
        mx[nl] = L === 3 ? Math.max(span[1][g], need[g + 2]) : span[31 - Math.clz32(L)][g];
      }
      for (let pw = 0; pw <= 8; pw++) {
        let bc = lc, bk = lk;
        for (let li = 0; li < nl && mx[li] <= pw; li++) {
          const L = RUN_LENS[li], c = 1 + 2 * pw * L + cost[(g + L) * 9 + pw];
          if (c < bc) { bc = c; bk = NIB_REPEAT + li; }
        }
        cost[g * 9 + pw] = bc;
        pick[g * 9 + pw] = bk;
      }
    }
    const gw = new Uint8Array(ng), nib = [];
    let pw = 0;
    for (let g = 0; g < ng;) {
      const k = pick[g * 9 + pw];
      nib.push(k);
      if (k < NIB_REPEAT) { pw = k; gw[g++] = k; }
      else for (let n = 0; n < NIB_GROUPS[k]; n++) gw[g++] = pw;
    }
    for (let k = 0; k < nib.length; k += 2)
      o.buf[o.len++] = nib[k] | (k + 1 < nib.length ? nib[k + 1] << 4 : 0);

    for (let g = 0; g < ng; g++) {
      const w = gw[g];
      let acc = 0, bits = 0;
      for (let i = 0; i < GROUP; i++) {
        acc |= z[g * GROUP + i] << bits; bits += w;
        while (bits >= 8) { o.buf[o.len++] = acc & 255; acc >>>= 8; bits -= 8; }
      }
    }
  }

  function encodeTile(o, sc, px, imgW, tx, ty, tw, th, ch) {
    const total = tw * th, start = o.len, raw = total * ch, tries = ch >= 3 ? 2 : 1;
    const mask = [0, 0], est = [0, 0];
    for (let t = 0; t < tries; t++) {
      const plane = sc.plane[t];
      for (let y = 0; y < th; y++) {
        let s = ((ty + y) * imgW + tx) * ch;
        for (let x = 0; x < tw; x++, s += ch) {
          const i = y * tw + x;
          if (ch < 3) { for (let c = 0; c < ch; c++) plane[c][i] = px[s + c]; continue; }
          const r = px[s], g = px[s + 1], b = px[s + 2];
          if (t === 0) {
            const oo = (r - b) & 255, tt = (b + (s8(oo) >> 1)) & 255, q = (g - tt) & 255;
            plane[0][i] = (tt + (s8(q) >> 1)) & 255;
            plane[1][i] = (oo + 128) & 255;
            plane[2][i] = (q + 128) & 255;
          } else {
            plane[0][i] = g;
            plane[1][i] = (r - g + 128) & 255;
            plane[2][i] = (b - g + 128) & 255;
          }
          if (ch === 4) plane[3][i] = px[s + 3];
        }
      }
      for (let c = 0; c < ch; c++) {
        const P = plane[c];
        let i = 1;
        while (i < total && P[i] === P[0]) i++;
        if (i === total) { mask[t] |= 1 << c; est[t] += 16; continue; }
        est[t] += chooseFilters(P, tw, th, sc.z[t][c], sc.filt[t][c]);
      }
    }
    const t = tries === 2 && est[1] < est[0] ? 1 : 0;
    o.reserve(5);
    o.buf[o.len++] = mask[t] | (t ? SUBGREEN : 0);
    for (let c = 0; c < ch; c++) if (mask[t] & (1 << c)) o.buf[o.len++] = sc.plane[t][c][0];
    for (let c = 0; c < ch; c++)
      if (!(mask[t] & (1 << c))) emitPlane(o, sc.z[t][c], sc.filt[t][c], tw, th);

    if (o.len - start > raw + 1) {
      o.len = start;
      o.reserve(raw + 1);
      o.buf[o.len++] = STORED;
      for (let y = 0; y < th; y++) {
        const s = ((ty + y) * imgW + tx) * ch;
        o.buf.set(px.subarray(s, s + tw * ch), o.len);
        o.len += tw * ch;
      }
    }
  }

  function encodeLevel(px, mw, mh, ch) {
    const tcx = Math.ceil(mw / TILE), tcy = Math.ceil(mh / TILE), tcount = tcx * tcy;
    const o = new Out(tcount * 4 + (mw * mh * ch >> 1));
    o.reserve(tcount * 4);
    o.len = tcount * 4;
    const mk = (n) => [0, 1, 2, 3].map(() => new Uint8Array(n));
    const sc = {
      plane: [mk(TILE_PX), mk(TILE_PX)],
      z: [mk(TILE_PX + GROUP), mk(TILE_PX + GROUP)],
      filt: [mk(TILE / BAND), mk(TILE / BAND)],
    };
    let t = 0;
    for (let ty = 0; ty < tcy; ty++)
      for (let tx = 0; tx < tcx; tx++, t++) {
        const x0 = tx * TILE, y0 = ty * TILE, start = o.len;
        encodeTile(o, sc, px, mw, x0, y0, Math.min(TILE, mw - x0), Math.min(TILE, mh - y0), ch);
        const n = o.len - start;
        o.buf[t * 4] = n & 255; o.buf[t * 4 + 1] = (n >>> 8) & 255;
        o.buf[t * 4 + 2] = (n >>> 16) & 255; o.buf[t * 4 + 3] = (n >>> 24) & 255;
      }
    return o.buf.subarray(0, o.len);
  }

  function encode(img) {
    const { width: W, height: H, channels: ch } = img;
    const mips = img.mips && img.mips.length ? img.mips : [img.pixels];
    const mipLevels = img.mipLevels || mips.length;
    if (!(W >= 1 && W <= MAX_DIM && H >= 1 && H <= MAX_DIM && ch >= 1 && ch <= 4 &&
          mipLevels >= 1 && mipLevels <= MAX_MIPS && mips.length >= mipLevels))
      throw new Error('YAPF: invalid image');
    const levels = [];
    for (let m = 0; m < mipLevels; m++) {
      const mw = Math.max(1, W >>> m), mh = Math.max(1, H >>> m);
      const px = m === 0 ? img.pixels : mips[m];
      if (!px || px.length < mw * mh * ch) throw new Error('YAPF: mip ' + m + ' has too few pixels');
      levels.push(encodeLevel(px, mw, mh, ch));
    }
    const idxEnd = 20 + 8 * mipLevels;
    let total = idxEnd;
    for (const l of levels) total += l.length;
    const out = new Uint8Array(total);
    out.set([0x59, 0x41, 0x50, 0x46, 1, ch, img.gpuFormat || 0, mipLevels, img.flags || 0]);
    const w32 = (p, v) => { out[p] = v & 255; out[p + 1] = (v >>> 8) & 255;
                            out[p + 2] = (v >>> 16) & 255; out[p + 3] = (v >>> 24) & 255; };
    w32(12, W); w32(16, H);
    let off = idxEnd;
    levels.forEach((l, m) => { w32(20 + 8 * m, off); w32(24 + 8 * m, l.length); out.set(l, off); off += l.length; });
    return out;
  }

  /* Any channel count → RGBA (for canvas ImageData). */
  function toRGBA(img, level) {
    const m = level || 0, px = img.mips ? img.mips[m] : img.pixels;
    const w = Math.max(1, img.width >>> m), h = Math.max(1, img.height >>> m), ch = img.channels;
    if (ch === 4) return new Uint8ClampedArray(px.buffer, px.byteOffset, w * h * 4);
    const out = new Uint8ClampedArray(w * h * 4);
    for (let i = 0, s = 0; i < w * h; i++, s += ch) {
      const o = i * 4;
      if (ch >= 3) { out[o] = px[s]; out[o + 1] = px[s + 1]; out[o + 2] = px[s + 2]; out[o + 3] = 255; }
      else { out[o] = out[o + 1] = out[o + 2] = px[s]; out[o + 3] = ch === 2 ? px[s + 1] : 255; }
    }
    return out;
  }

  return { decode, encode, toRGBA, decodeTexture, textureToRGBA, decodeBlocks, surfaceIndex,
           checksum: (b) => checksum(b, 0, b.length), YapfError, GPU, FLAG, NEED,
           VERSION: 1 /* written by encode */, READS: [1, 2] };
}));