app.js

// ===========================================================================
// PALETTE — pulled from CSS variables so tokens stay single-source-of-truth
// ===========================================================================
const CSS = getComputedStyle(document.documentElement);
const PALETTE = [
  CSS.getPropertyValue('--palette-1').trim(),
  CSS.getPropertyValue('--palette-2').trim(),
  CSS.getPropertyValue('--palette-3').trim(),
  CSS.getPropertyValue('--palette-4').trim(),
  CSS.getPropertyValue('--palette-5').trim(),
  CSS.getPropertyValue('--palette-6').trim(),
  CSS.getPropertyValue('--palette-7').trim(),
  CSS.getPropertyValue('--palette-8').trim(),
  CSS.getPropertyValue('--palette-9').trim(),
  CSS.getPropertyValue('--palette-10').trim(),
  CSS.getPropertyValue('--palette-11').trim(),
  CSS.getPropertyValue('--palette-12').trim(),
];

/** Brighten an HSL-mapped color for the inner tick mark (and voronoi hovers). */
function luminousVariant(hex, lightnessBoost = 0.4, saturationBoost = 0.12) {
  const c = d3.hsl(hex);
  c.l = Math.min(0.9, c.l + lightnessBoost);
  c.s = Math.min(1, c.s + saturationBoost);
  return c.formatHex();
}

/** Format a number as an integer + <span class="decimal">.Mk</span>. */
function formatRows(n) {
  if (n >= 1_000_000) {
    const v = n / 1_000_000;
    const [whole, frac] = v.toFixed(1).split('.');
    return `${whole}<span class="decimal">.${frac}M</span>`;
  }
  if (n >= 1_000) {
    const v = n / 1_000;
    const [whole, frac] = v.toFixed(1).split('.');
    return `${whole}<span class="decimal">.${frac}k</span>`;
  }
  return String(n);
}
function formatShort(n) {
  if (n >= 1_000_000) return (n / 1_000_000).toFixed(1).replace(/\.0$/, '') + 'M';
  if (n >= 1_000)     return (n / 1_000).toFixed(1).replace(/\.0$/, '') + 'k';
  return String(n);
}

// Upgrade hero stat numbers to support a decimal span
document.querySelectorAll('.stat .num').forEach(el => {
  const raw = el.getAttribute('data-value');
  const m = raw && raw.match(/^([~≈]?[\d,]+)(\.[\d]+)?([A-Za-z+]+)?$/);
  if (!m) { el.textContent = raw || ''; return; }
  const [, whole, frac = '', suffix = ''] = m;
  el.innerHTML = frac || suffix
    ? `${whole}<span class="decimal">${frac}${suffix}</span>`
    : whole;
});

// ===========================================================================
// DATASET CATALOG
// ===========================================================================
const DATASETS = [
  {
    key: "speech",
    title: "Multilingual Synthetic Speech",
    tagline: "Zero-shot voice cloning with Qwen3-TTS across 9 languages",
    raw: { repo: "Reubencf/multilingual-synthetic-tts", rows: 68677 },
    adaption: { repo: "Reubencf/Adaption-multilingual-speech", rows: 10274 },
    languages: "en, ja, zh, ko, de, es, fr, ru, pt",
    modality: "audio + text",
    license: "open / synthetic",
    schema: ["audio", "text", "language", "language_name", "style", "voice", "sample_rate"],
    model: "Qwen3-TTS-12Hz-1.7B-Base",
    group: "paired"
  },
  {
    key: "sentences",
    title: "Multilingual Sentences (text-only)",
    tagline: "Text projection of the TTS corpus — ready for Adaption",
    raw: null,
    adaption: { repo: "Reubencf/Adaption-multilingual-sentences", rows: 10000 },
    languages: "ja, ru, ko, de, es, pt, zh, en, fr + 114 more",
    modality: "text",
    license: "open",
    schema: ["text", "enhanced_prompt", "enhanced_completion", "language", "voice", "style"],
    group: "paired"
  },
  {
    key: "music",
    title: "Music — FMA Labeled",
    tagline: "Creative-Commons music tracks with lyrics, genre, mood, BPM, key",
    raw: { repo: "Reubencf/fma-labeled", rows: 29000 },
    adaption: { repo: "Reubencf/adaption-music-style-prompts", rows: 9950 },
    languages: "en",
    modality: "audio + text",
    license: "CC-BY / CC0 (source-dependent)",
    schema: ["audio", "lyrics", "genre", "sub_genres", "mood", "instruments", "bpm", "key", "vocal_type", "energy", "era", "quality"],
    model: "gemini-flash-latest",
    group: "paired"
  },
  {
    key: "street",
    title: "StreetView Global",
    tagline: "Globally-sampled Mapillary street images with scene classification",
    raw: { repo: "Reubencf/streetview-global", rows: 30000 },
    adaption: { repo: "Reubencf/adaption-street-scene-descriptions", rows: 10100 },
    languages: "en",
    modality: "image + text",
    license: "CC-BY-SA-4.0",
    schema: ["image", "scene_description", "setting", "weather", "time_of_day", "road_type", "infrastructure", "lat", "lon", "compass"],
    group: "paired"
  },
  {
    key: "magazines",
    title: "Magazines Multilingual VQA",
    tagline: "Public-domain magazine OCR in 40+ source languages (including low-resource)",
    raw: { repo: "Reubencf/magazines-multilingual-vqa", rows: 29039 },
    adaption: { repo: "Reubencf/adaption-multilingual-doc-qa", rows: 8800 },
    languages: "ar, de, en, es, fr, hi, it, ja, pt, zh + 35 more (Afrikaans, Amharic, Yoruba, Yiddish, Bengali, Santali, Somali, Vietnamese, Russian, Maithili, Tibetan, …)",
    modality: "image + text",
    license: "CC-BY-4.0",
    schema: ["image", "ocr_text", "english_description", "question", "answer", "target_language", "page_type"],
    model: "Gemma 4 31B via vLLM",
    group: "paired"
  },
  {
    key: "lowresource",
    title: "Low-Resource Doc Q/A",
    tagline: "Low-resource-language slice of the magazines corpus",
    raw: null,
    adaption: { repo: "Reubencf/Adaption-low-resource-doc-qa", rows: 10200 },
    languages: "Afrikaans, Amharic, Yoruba, Yiddish, Bengali, Santali, Somali, Vietnamese, Maithili, Tigrinya, Meitei, Lao, …",
    modality: "image + text",
    license: "CC-BY-4.0",
    schema: ["image", "ocr_text", "question", "answer", "source_language"],
    group: "paired"
  },
  {
    key: "captions",
    title: "Multilingual Image Captions",
    tagline: "English + multilingual captions with bounding-box visualizations",
    raw: { repo: "Reubencf/multilingual-image-annotations", rows: 464 },
    adaption: { repo: "Reubencf/adaption-multilingual-image-captions", rows: 462 },
    languages: "en, es, fr, hi, zh, ar, pt",
    modality: "image + text",
    license: "CC-BY-4.0",
    schema: ["image", "boxed_image", "description_en", "descriptions", "vqa", "detections"],
    model: "Gemma 4 31B",
    group: "paired"
  },
  {
    key: "frontend",
    title: "Frontend Coding",
    tagline: "Hand-curated HTML / Tailwind / JS prompts and completions",
    raw: { repo: "Reubencf/frontend-coding", rows: 500 },
    adaption: { repo: "Reubencf/frontend-html-tailwind-js", rows: 145 },
    languages: "en",
    modality: "text (code)",
    license: "MIT",
    schema: ["prompt", "previous_code", "code", "reasoning"],
    group: "paired"
  },
  {
    key: "news2026",
    title: "Current Affairs 2026",
    tagline: "2026 Wikipedia current-events Q/A with RAG grounding (through Apr 9, 2026)",
    raw: { repo: "Reubencf/future-news-events-2026", rows: 5447 },
    adaption: { repo: "Reubencf/current-affairs-2026", rows: 5339 },
    languages: "en",
    modality: "text",
    license: "open",
    schema: ["question", "answer", "enhanced_prompt", "enhanced_completion", "reasoning_trace", "date", "event_id", "section", "source"],
    model: "Cohere Command R + RAG",
    group: "paired"
  },
  {
    key: "news2025",
    title: "Current Affairs 2025",
    tagline: "2025 global events Q/A",
    raw: { repo: "Reubencf/2025_events", rows: 5390 },
    adaption: { repo: "Reubencf/current-affairs-2025", rows: 5390 },
    languages: "en",
    modality: "text",
    license: "open",
    schema: ["question", "answer", "enhanced_prompt", "enhanced_completion"],
    group: "paired"
  },
  {
    key: "news2024",
    title: "Current Affairs 2024",
    tagline: "2024 global events Q/A",
    raw: { repo: "Reubencf/2024_events", rows: 5190 },
    adaption: { repo: "Reubencf/current-affairs-2024", rows: 5190 },
    languages: "en",
    modality: "text",
    license: "open",
    schema: ["question", "answer", "enhanced_prompt", "enhanced_completion"],
    group: "paired"
  },
  {
    key: "news2023",
    title: "Current Affairs 2023",
    tagline: "2023 global events Q/A",
    raw: { repo: "Reubencf/2023_events", rows: 4667 },
    adaption: { repo: "Reubencf/current-affairs-2023", rows: 4667 },
    languages: "en",
    modality: "text",
    license: "open",
    schema: ["question", "answer", "enhanced_prompt", "enhanced_completion"],
    group: "paired"
  },
  // Pre-training pools — now included in the raw donut too.
  {
    key: "polyaudio",
    title: "PolyglotAudio",
    tagline: "Broad multilingual audio pre-training pool",
    raw: { repo: "Reubencf/PolyglotAudio", rows: 1200000 },
    adaption: null,
    languages: "multilingual",
    modality: "audio + text",
    license: "open",
    schema: ["audio", "text", "language"],
    group: "paired"
  },
  {
    key: "polytext",
    title: "PolyglotText",
    tagline: "Large multilingual text pre-training pool",
    raw: { repo: "Reubencf/PolyglotText", rows: 13400000 },
    adaption: null,
    languages: "multilingual",
    modality: "text",
    license: "open",
    schema: ["text", "language"],
    group: "paired"
  },
];

// Stable color per dataset key — cycles through PALETTE
const datasetColor = d3.scaleOrdinal(PALETTE).domain(DATASETS.map(d => d.key));
DATASETS.forEach(d => { d.color = datasetColor(d.key); });

// ===========================================================================
// DONUT CHART (D3 — used for both Raw/Adaption donuts and the modality donut)
// ===========================================================================
const tooltipEl = document.getElementById('donut-tooltip');

// Per-SVG selection state for drill-down (scale-up selected, dim others).
const donutState = new Map(); // svgId -> { selectedKey, paths, arcGen }

function renderDonut({ svgId, centerId, field, datasets, getValue, getKey, getTitle, getColor, getMeta, colorScale, topLabel, bottomLabel, topIcon, bottomIcon, sizing = 'linear' }) {
  const svg = d3.select('#' + svgId);
  svg.selectAll('*').remove();

  const bbox = svg.node().getBoundingClientRect();
  const size = Math.min(bbox.width, bbox.height);
  const outerR = size / 2 - 6;
  const innerR = outerR * 0.62;
  svg.attr('viewBox', `${-size / 2} ${-size / 2} ${size} ${size}`);

  const filtered = datasets.filter(d => getValue(d) > 0);
  const total = d3.sum(filtered, getValue);
  const count = filtered.length;

  // Sizing strategy for the arc:
  //   "linear"   — true proportions (small slices can vanish)
  //   "log"      — power-compressed so tiny datasets stay visible while the
  //                big ones (PolyglotText 13M+, PolyglotAudio 1M+) still read
  //                as clearly the largest slices
  //   "sqrt"     — lighter square-root compression
  // Tooltip + center numbers always show real values.
  const sizeValue = d => {
    const v = getValue(d);
    if (sizing === 'log')  return Math.pow(v + 1, 0.38);
    if (sizing === 'sqrt') return Math.sqrt(v + 1);
    return v;
  };

  const pie = d3.pie().value(sizeValue).sort(null).padAngle(0.022);
  const arcs = pie(filtered);
  const arcGen = d3.arc().innerRadius(innerR).outerRadius(outerR).cornerRadius(3);
  const resolveColor = getColor || (x => datasetColor(getKey(x)));

  const g = svg.append('g');

  // Slice paths
  const paths = g.selectAll('path')
    .data(arcs)
    .join('path')
    .attr('class', 'donut-slice')
    .attr('fill', d => resolveColor(d.data))
    .attr('stroke', '#000000')
    .attr('stroke-width', 2)
    .attr('stroke-linejoin', 'round');

  // Radial sweep: interpolate endAngle from startAngle → target, so arcs
  // literally grow around the ring from 0° of arc to their full sweep.
  paths.each(function (d) {
    const [cx, cy] = arcGen.centroid(d);
    this._centroid = [cx, cy];
    this._current = { startAngle: d.startAngle, endAngle: d.startAngle, padAngle: d.padAngle };
  });
  paths.transition()
    .delay((d, i) => i * 80)
    .duration(1100)
    .ease(d3.easeCubicOut)
    .attrTween('d', function (d) {
      const interp = d3.interpolate(this._current, d);
      this._current = interp(1);
      return t => arcGen(interp(t));
    });



  // Hover tooltip + click drill-down
  paths
    .on('mouseenter', function (ev, d) {
      const nm = getTitle(d.data);
      const v = getValue(d.data);
      const meta = getMeta ? getMeta(d.data) : '';
      tooltipEl.innerHTML =
        `<div class="t-name">${nm}</div>` +
        `<div class="t-meta">${v.toLocaleString()} rows` +
        (meta ? ` · ${meta}` : '') + `</div>`;
      gsap.to(tooltipEl, { opacity: 1, duration: 0.15, overwrite: true });
    })
    .on('mousemove', function (ev) {
      tooltipEl.style.left = (ev.clientX + 14) + 'px';
      tooltipEl.style.top  = (ev.clientY + 14) + 'px';
    })
    .on('mouseleave', function () {
      gsap.to(tooltipEl, { opacity: 0, duration: 0.12, overwrite: true });
    })
    .on('click', function (ev, d) {
      const key = getKey(d.data);
      focusDonutSlice(svgId, this, key);
      if (typeof showDetails === 'function') showDetails(key);
    });

  // Cache for drill-down reset logic.
  donutState.set(svgId, { paths, arcGen, resolveColor });

  // Center content — start at 0 and count up with GSAP.
  if (centerId) {
    const centerEl = document.getElementById(centerId);
    const topIconHtml    = topIcon    ? `<span class="icon">${topIcon}</span>` : '';
    const bottomIconHtml = bottomIcon ? `<span class="icon">${bottomIcon}</span>` : '';
    centerEl.innerHTML =
      `<div class="center-item top">

        <div class="center-label">${topIconHtml}${topLabel}</div>

        <div class="center-number js-count-top">0</div>

      </div>

      <div class="center-item bottom">

        <div class="center-number js-count-bottom">0</div>

        <div class="center-label">${bottomLabel}${bottomIconHtml}</div>

      </div>`;

    const topEl = centerEl.querySelector('.js-count-top');
    const bottomEl = centerEl.querySelector('.js-count-bottom');

    const topObj = { v: 0 };
    gsap.to(topObj, {
      v: count,
      duration: 1.0,
      ease: 'power2.out',
      delay: 0.55,
      onUpdate: () => { topEl.textContent = Math.floor(topObj.v); },
      onComplete: () => { topEl.textContent = count; }
    });

    const bottomObj = { v: 0 };
    gsap.to(bottomObj, {
      v: total,
      duration: 1.6,
      ease: 'power2.out',
      delay: 0.65,
      onUpdate: () => { bottomEl.innerHTML = formatRows(Math.floor(bottomObj.v)); },
      onComplete: () => { bottomEl.innerHTML = formatRows(total); }
    });

    gsap.from(`#${centerId} .center-label`, { y: 14, opacity: 0, duration: 0.55, ease: 'power3.out', delay: 0.45, stagger: 0.15 });
    gsap.from(`#${centerId} .center-number`, { y: 10, opacity: 0, duration: 0.55, ease: 'power3.out', delay: 0.55, stagger: 0.15 });

    // Space out the top/bottom blocks since the divider is gone.
    centerEl.querySelector('.center-item.bottom').style.marginTop = '14px';
  }

  return paths;
}

/** Click drill-down: scale up clicked slice, dim the rest, toggle on re-click. */
function focusDonutSlice(svgId, clickedEl, clickedKey) {
  const state = donutState.get(svgId);
  if (!state) return;
  const { paths, arcGen } = state;

  // Toggle off if clicking the already-selected slice
  if (state.selectedKey === clickedKey) {
    resetDonutFocus(svgId);
    return;
  }
  state.selectedKey = clickedKey;

  paths.nodes().forEach((node, i) => {
    const d = paths.data()[i];
    const isSelected = node === clickedEl;
    if (isSelected) {
      const [cx, cy] = node._centroid || arcGen.centroid(d);
      gsap.to(node, {
        scale: 1.08,
        opacity: 1,
        svgOrigin: `${cx} ${cy}`,
        filter: 'drop-shadow(0 0 14px rgba(255,255,255,0.35)) brightness(1.15)',
        duration: 0.45,
        ease: 'power2.out',
        overwrite: 'auto'
      });
    } else {
      gsap.to(node, {
        scale: 1,
        opacity: 0.3,
        filter: 'none',
        duration: 0.35,
        ease: 'power2.out',
        overwrite: 'auto'
      });
    }
  });
}

function resetDonutFocus(svgId) {
  const state = donutState.get(svgId);
  if (!state) return;
  state.selectedKey = null;
  state.paths.nodes().forEach(node => {
    gsap.to(node, {
      scale: 1, opacity: 1, filter: 'none',
      duration: 0.35, ease: 'power2.out', overwrite: 'auto'
    });
  });
}

// ---- Raw vs Adaption donuts ----
// The Raw donut shows every dataset that has a raw repo (including the
// PolyglotText / PolyglotAudio pre-training pools). The Adaption donut shows
// every dataset with an Adaption-remastered version. renderDonut() filters
// out zero-value entries automatically.
renderDonut({
  svgId: 'chart-raw',
  centerId: 'center-raw',
  field: 'raw',
  datasets: DATASETS,
  getValue: d => (d.raw && d.raw.rows) || 0,
  getKey: d => d.key,
  getTitle: d => d.title,
  getMeta: d => d.raw ? d.raw.repo : '',
  topLabel: 'RAW DATASETS',
  bottomLabel: 'ROWS',
  topIcon: '',
  bottomIcon: '',
  sizing: 'log',   // compress so tiny datasets still get a visible slice
});

renderDonut({
  svgId: 'chart-adaption',
  centerId: 'center-adaption',
  field: 'adaption',
  datasets: DATASETS,
  getValue: d => (d.adaption && d.adaption.rows) || 0,
  getKey: d => d.key,
  getTitle: d => d.title,
  getMeta: d => d.adaption ? d.adaption.repo : '',
  topLabel: 'ADAPTION SETS',
  bottomLabel: 'ROWS',
  topIcon: '',
  bottomIcon: '',
});

// ---- Modality donut ----
const MODALITIES = [
  { key: 'text',  name: 'Text',  count: 5 },
  { key: 'audio', name: 'Audio', count: 3 },
  { key: 'image', name: 'Image', count: 3 },
  { key: 'code',  name: 'Code',  count: 1 },
];
const modalityColor = d3.scaleOrdinal(PALETTE).domain(MODALITIES.map(m => m.key));

renderDonut({
  svgId: 'chart-modality',
  centerId: 'center-modality',
  field: 'count',
  datasets: MODALITIES,
  getValue: d => d.count,
  getKey: d => d.key,
  getTitle: d => d.name,
  getColor: d => modalityColor(d.key),
  getMeta: d => `${d.count} datasets`,
  topLabel: 'MODALITIES',
  bottomLabel: 'DATASETS',
  topIcon: '',
  bottomIcon: '',
});

// ===========================================================================
// DETAILS CARD — rendered on slice click with GSAP reveal
// ===========================================================================
function hideLanguageDetails() {
  // No-op placeholder — currently we share the single details card; click-
  // another to switch. Kept as an explicit symbol for future extension.
}

function showLanguageDetails(langData, color) {
  const card = document.getElementById('details-card');
  card.style.display = '';

  // Per-dataset breakdown for this language.
  const breakdown = DATASET_LANGS
    .map(d => ({ dataset: d.name, key: d.key, rows: d.langs[langData.code] || 0 }))
    .filter(d => d.rows > 0)
    .sort((a, b) => b.rows - a.rows);

  const rows = breakdown.map(b =>
    `<div class="kv"><div class="k">${b.dataset}</div><div class="v"><strong>${formatShort(b.rows)}</strong>

      <span style="color:var(--muted);font-size:0.85em">(${b.rows.toLocaleString()})</span></div></div>`
  ).join('');

  card.innerHTML = `

    <h3>

      <span class="swatch" style="background:${color}"></span>

      ${langData.name} <span style="color:var(--muted);font-weight:400;font-size:0.9rem">(${langData.code})</span>

    </h3>

    <p class="tagline">Total across the raw corpus: <strong>${langData.value.toLocaleString()}</strong> rows.</p>

    <div class="kv-grid">${rows}</div>

  `;

  gsap.fromTo(card,
    { y: 80, opacity: 0 },
    { y: 0, opacity: 1, duration: 0.75, ease: 'power4.out' }
  );
  gsap.from(card.querySelectorAll('.kv'), {
    y: 18, opacity: 0, duration: 0.45, ease: 'power3.out',
    stagger: 0.05, delay: 0.2
  });

  card.scrollIntoView({ behavior: 'smooth', block: 'nearest' });
}

function showDetails(key) {
  const d = DATASETS.find(x => x.key === key);
  if (!d) return;
  const card = document.getElementById('details-card');
  card.style.display = '';

  const repoLink = info => info
    ? `<a href="https://huggingface.co/datasets/${info.repo}" target="_blank">${info.repo}</a>`
    : `<span style="color:var(--muted);">—</span>`;
  const rowsCell = info => info
    ? `<strong>${formatShort(info.rows)}</strong> <span style="color:var(--muted);font-size:0.85em">(${info.rows.toLocaleString()})</span>`
    : `<span style="color:var(--muted);">—</span>`;

  card.innerHTML = `

    <h3>

      <span class="swatch" style="background:${d.color}"></span>

      ${d.title}

    </h3>

    <p class="tagline">${d.tagline}</p>

    <div class="kv-grid">

      <div class="kv"><div class="k">Raw repo</div><div class="v">${repoLink(d.raw)}</div></div>

      <div class="kv"><div class="k">Raw rows</div><div class="v">${rowsCell(d.raw)}</div></div>

      <div class="kv"><div class="k">Adaption repo</div><div class="v">${repoLink(d.adaption)}</div></div>

      <div class="kv"><div class="k">Adaption rows</div><div class="v">${rowsCell(d.adaption)}</div></div>

      <div class="kv"><div class="k">Modality</div><div class="v">${d.modality}</div></div>

      <div class="kv"><div class="k">License</div><div class="v">${d.license}</div></div>

      ${d.model ? `<div class="kv"><div class="k">Annotator</div><div class="v">${d.model}</div></div>` : ''}

      <div class="kv"><div class="k">Languages</div><div class="v">${d.languages}</div></div>

    </div>

    <div class="kv" style="margin-top:18px;">

      <div class="k">Schema</div>

      <div class="schema-list">${d.schema.map(c => `<code>${c}</code>`).join('')}</div>

    </div>

  `;

  // Elegant slide-in from the bottom with power4.out.
  gsap.fromTo(card,
    { y: 80, opacity: 0 },
    { y: 0, opacity: 1, duration: 0.75, ease: 'power4.out' }
  );
  gsap.from(card.querySelectorAll('.kv'), {
    y: 18, opacity: 0, duration: 0.45, ease: 'power3.out',
    stagger: 0.05, delay: 0.2
  });

  card.scrollIntoView({ behavior: 'smooth', block: 'nearest' });
}

// ===========================================================================
// INITIAL PAGE LOAD — hero image → hero stats → chart cards, staggered.
// ===========================================================================
const loadTl = gsap.timeline();
loadTl
  .from('.hero-img', { y: 20, opacity: 0, duration: 0.9, ease: 'power3.out' })
  .from('.stat',     { y: 20, opacity: 0, duration: 0.7, ease: 'power3.out', stagger: 0.15 }, '-=0.5')
  .from('.chart-card', { y: 20, opacity: 0, duration: 0.8, ease: 'power3.out', stagger: 0.15 }, '-=0.3');

// ===========================================================================
// LANGUAGE DATA (for the Voronoi treemap)
// ===========================================================================
const LANG_NAMES = {
  tr: "Turkish", ru: "Russian", it: "Italian", en: "English", eo: "Esperanto",
  hu: "Hungarian", de: "German", fr: "French", pt: "Portuguese", mk: "Macedonian",
  es: "Spanish", he: "Hebrew", fi: "Finnish", ber: "Berber", nl: "Dutch",
  pl: "Polish", sr: "Serbian", mr: "Marathi", el: "Greek", da: "Danish",
  cs: "Czech", sv: "Swedish", bg: "Bulgarian", la: "Latin", zh: "Mandarin",
  ro: "Romanian", ia: "Interlingua", ja: "Japanese", tok: "Toki Pona",
  lfn: "Lingua Franca Nova", uk: "Ukrainian", tt: "Tatar", tl: "Tagalog",
  id: "Indonesian", nb: "Norwegian B.", lt: "Lithuanian", az: "Azerbaijani",
  ie: "Interlingue", tlh: "Klingon", jbo: "Lojban", mhr: "Meadow Mari",
  bn: "Bengali", fa: "Persian", br: "Breton", ilo: "Ilocano", ar: "Arabic",
  ceb: "Cebuano", hi: "Hindi", vi: "Vietnamese", pam: "Kapampangan",
  hy: "Armenian", be: "Belarusian", ko: "Korean", yue: "Cantonese",
  ca: "Catalan", kab: "Kabyle", af: "Afrikaans", am: "Amharic", yi: "Yiddish",
  sat: "Santali", so: "Somali", te: "Telugu", ne: "Nepali", pa: "Punjabi",
  ur: "Urdu", ta: "Tamil", ml: "Malayalam", th: "Thai", or: "Odia",
  sd: "Sindhi", gu: "Gujarati", kn: "Kannada", my: "Burmese", bo: "Tibetan",
  lo: "Lao", mni: "Meitei", kk: "Kazakh", oc: "Occitan", hr: "Croatian",
  sk: "Slovak", et: "Estonian", sl: "Slovenian", is: "Icelandic", ms: "Malay",
  sq: "Albanian", hsb: "Upper Sorbian", dsb: "Lower Sorbian", mai: "Maithili",
  kha: "Khasi", dtp: "Kadazan", yo: "Yoruba", sw: "Swahili", cy: "Welsh",
  ga: "Irish", gd: "Scottish Gaelic", ti: "Tigrinya", os: "Ossetian",
  sa: "Sanskrit", ug: "Uyghur", uz: "Uzbek", ka: "Georgian", eu: "Basque",
  vo: "Volapük", ido: "Ido", nov: "Novial", avk: "Kotava", ldn: "Láadan",
  afh: "Afrihili", lzh: "Classical Chinese", non: "Old Norse", ang: "Old English",
  grc: "Ancient Greek", sux: "Sumerian", fro: "Old French", cbk: "Chavacano",
  zsm: "Standard Malay", war: "Waray", kw: "Cornish", nah: "Nahuatl",
  kek: "Q'eqchi'", hif: "Fiji Hindi", crh: "Crimean Tatar", sah: "Sakha",
  ext: "Extremaduran", csb: "Kashubian", sgs: "Samogitian", cha: "Chamorro",
  tvl: "Tuvaluan", mi: "Maori", lin: "Lingala", arq: "Algerian Arabic",
  arz: "Egyptian Arabic", orv: "Old East Slavic", prg: "Old Prussian",
  chv: "Chuvash", bar: "Bavarian", pms: "Piedmontese", egl: "Emilian",
  jav: "Javanese", sun: "Sundanese", hoc: "Ho", zza: "Zaza",
  rif: "Riffian Berber", nog: "Nogai", km: "Khmer",
};

const DATASET_LANGS = [
  {
    key: "polytext", name: "PolyglotText",
    langs: {
      tr: 1767000, ru: 1695000, it: 1588000, en: 1337000, eo: 1171000,
      hu: 817000, de: 675000, fr: 520000, pt: 470000, mk: 398000,
      es: 358000, he: 272000, fi: 263000, ber: 180000, nl: 125000,
      pl: 118000, sr: 106000, mr: 96000, el: 94000, da: 90000,
      cs: 72000, sv: 71000, bg: 70000, la: 66000, zh: 58000, ro: 56000,
      ia: 54000, ja: 43000, tok: 39000, lfn: 38000, uk: 38000, tt: 33000,
      tl: 31000, id: 31000, nb: 31000, lt: 29000, az: 25000, ie: 24000,
      tlh: 23000, jbo: 21000, mhr: 19000, bn: 19000, fa: 17000, br: 17000,
      ilo: 17000, ar: 16000, ceb: 15000, hi: 13000, vi: 11000, pam: 11000,
      hy: 9000, be: 9000, ko: 9000,
      cbk: 19000, sk: 8000, vo: 8000, oc: 8000, et: 8000,
      war: 6700, ms: 6700, hr: 6700, eu: 6700, yi: 5400, af: 5400,
      km: 4000, ca: 4000, kha: 4000, dtp: 4000, zza: 4000, is: 4000,
      avk: 4000, ga: 4000, hoc: 4000, sl: 4000, sq: 4000, chv: 4000,
      kw: 4000, sux: 2700, ang: 2700, pms: 2700, prg: 2700, ug: 2700,
      lzh: 2700, egl: 2700, ur: 2700, sah: 2700, nds: 2700, mi: 2700,
      tvl: 1400, cha: 1400, th: 1400, cy: 1400, non: 1400, yo: 1400,
      lin: 1400, grc: 1400, arq: 1400, orv: 1400, sw: 1400, rif: 1400,
      crh: 1400, hif: 1400, jav: 1400, sun: 1400, hsb: 1400, dsb: 1400,
      amh: 1400, csb: 1400, sgs: 1400, ext: 1400, nov: 1400, nog: 1400,
      arz: 1400, nah: 1400, ido: 1400, afh: 1400, kk: 1400,
    }
  },
  {
    key: "polyaudio", name: "PolyglotAudio",
    langs: {
      en: 698000, es: 261000, eo: 105000, de: 32000, fr: 16000,
      ru: 9200, pl: 8800, ber: 6600, nl: 5900, it: 5900,
      yue: 4300, pt: 3300, ja: 1400, mr: 1200, ca: 505,
      cs: 410, zh: 110, fi: 93, hu: 87, uk: 38,
      he: 16, tok: 5, kab: 5,
    }
  },
  {
    key: "tts", name: "multilingual-synthetic-tts",
    langs: {
      ja: 13951, ru: 9105, de: 8972, ko: 8129, es: 7917,
      pt: 5438, zh: 5417, en: 5157, fr: 4551,
    }
  },
  {
    key: "magazines", name: "magazines-multilingual-vqa",
    langs: {
      de: 4412, fr: 3279, ru: 2762, pt: 2047, vi: 1637, bn: 1598,
      en: 1004, af: 826, ar: 156, it: 136, fa: 132, te: 132,
      ja: 130, ne: 108, pa: 100, ur: 98, nl: 95, tr: 85, zh: 83,
      ta: 68, ml: 64, id: 43, th: 47, am: 123, yi: 108, sat: 85,
      so: 25, hi: 15, es: 10, mr: 9, kn: 8, or: 17, sd: 3,
      mai: 1021, la: 146, bo: 25, be: 8, da: 6, ko: 4, bg: 4,
      os: 3, sa: 3, my: 3, oc: 1, gd: 1, ti: 1, hy: 1, pl: 1,
      mni: 1, uk: 1, lo: 1, kk: 1,
    }
  },
  { key: "fma",              name: "fma-labeled",                   langs: { en: 29000 } },
  { key: "streetview",       name: "streetview-global",             langs: { en: 30000 } },
  { key: "current_affairs",  name: "current-affairs (raw, 2023-26)", langs: { en: 20694 } },
  { key: "frontend",         name: "frontend-coding",               langs: { en: 500 } },
  {
    key: "image_ann", name: "multilingual-image-annotations",
    langs: { en: 464, es: 464, fr: 464, hi: 464, zh: 464, ar: 464, pt: 464 }
  },
];

// Aggregate totals across the raw corpus
const langTotals = {};
for (const d of DATASET_LANGS) {
  for (const [lang, n] of Object.entries(d.langs)) {
    langTotals[lang] = (langTotals[lang] || 0) + n;
  }
}
const langEntries = Object.entries(langTotals)
  .sort((a, b) => b[1] - a[1])
  .map(([code, n]) => ({
    code,
    name: LANG_NAMES[code] || code,
    value: n,
    sizeValue: Math.log10(n + 10),
  }));

// ===========================================================================
// VORONOI TREEMAP (D3) — palette quantile coloring, black strokes
// ===========================================================================
(function renderVoronoi() {
  const container = document.getElementById('chart-treemap');
  const tooltip = document.getElementById('voronoi-tooltip');

  if (typeof d3 === 'undefined' || !d3.voronoiTreemap) {
    container.insertAdjacentHTML('beforeend',
      `<div style="color:#ff8a8a;padding:24px;text-align:center;font-size:0.9rem">

        Voronoi treemap libraries failed to load. Check your network / CSP.

      </div>`);
    return;
  }

  // Map language size buckets onto PALETTE via quantiles, so cells naturally
  // cluster by tonal groups.
  const colorScale = d3.scaleQuantile()
    .domain(langEntries.map(e => e.sizeValue))
    .range(PALETTE);

  function draw() {
    container.querySelectorAll('svg').forEach(s => s.remove());

    const rect = container.getBoundingClientRect();
    const width  = Math.max(320, rect.width);
    const height = Math.max(320, rect.height);

    // Circular clip polygon
    const clipPad = 6;
    const cx = width / 2, cy = height / 2;
    const r  = Math.min(width, height) / 2 - clipPad;
    const N  = 96;
    const clipPolygon = d3.range(N).map(i => [
      cx + r * Math.cos((i / N) * 2 * Math.PI),
      cy + r * Math.sin((i / N) * 2 * Math.PI),
    ]);

    const root = d3.hierarchy({ name: 'root', children: langEntries })
      .sum(d => d.sizeValue);

    const treemap = d3.voronoiTreemap()
      .clip(clipPolygon)
      .convergenceRatio(0.005)
      .maxIterationCount(120)
      .minWeightRatio(0.01);
    treemap(root);

    const svg = d3.select(container).append('svg')
      .attr('viewBox', `0 0 ${width} ${height}`)
      .attr('preserveAspectRatio', 'xMidYMid meet');
    const g = svg.append('g');

    // Outer circle outline
    g.append('circle')
      .attr('cx', cx).attr('cy', cy).attr('r', r + 1)
      .attr('fill', 'none')
      .attr('stroke', '#1f1f1f')
      .attr('stroke-width', 1);

    const leaves = root.leaves();

    const cells = g.selectAll('path.voronoi-cell')
      .data(leaves)
      .join('path')
      .attr('class', 'voronoi-cell')
      .attr('d', d => 'M' + d.polygon.map(p => p.join(',')).join('L') + 'Z')
      .attr('fill', d => colorScale(d.data.sizeValue))
      .attr('stroke', '#000000')
      .attr('stroke-width', 1.2)
      .attr('stroke-linejoin', 'round');

    // Record centroid per cell so we can scale from the cell's own center.
    cells.each(function (leaf) {
      const [cx, cy] = leaf.site || d3.polygonCentroid(leaf.polygon);
      this._centroid = [cx, cy];
    });

    // Mosaic build: fade + scale up from each cell's own centroid, staggered.
    cells.nodes().forEach((node, i) => {
      const [cx, cy] = node._centroid;
      gsap.fromTo(node,
        { scale: 0, opacity: 0, svgOrigin: `${cx} ${cy}` },
        { scale: 1, opacity: 1, svgOrigin: `${cx} ${cy}`,
          duration: 0.55, ease: 'power3.out', delay: i * 0.012 }
      );
    });

    // Labels — sized by cell area; smaller cells hide the name, tiny ones only show on hover.
    function polyArea(pts) {
      let a = 0;
      for (let i = 0, n = pts.length; i < n; i++) {
        const [x1, y1] = pts[i], [x2, y2] = pts[(i + 1) % n];
        a += x1 * y2 - x2 * y1;
      }
      return Math.abs(a) / 2;
    }

    leaves.forEach(leaf => {
      const area = polyArea(leaf.polygon);
      const side = Math.sqrt(area);
      const [x, y] = leaf.site || d3.polygonCentroid(leaf.polygon);
      const d = leaf.data;

      if (side >= 44) {
        const nameSize = Math.max(10, Math.min(18, side / 6));
        const codeSize = Math.max(9, Math.min(13, side / 9));
        const text = g.append('text')
          .datum(leaf.data)
          .attr('class', 'voronoi-label')
          .attr('x', x).attr('y', y - 2)
          .attr('font-size', nameSize);
        text.append('tspan').text(d.name);
        text.append('tspan')
          .attr('class', 'code')
          .attr('x', x).attr('dy', nameSize * 0.95)
          .attr('font-size', codeSize)
          .text(`${d.code} · ${formatShort(d.value)}`);
      } else if (side >= 22) {
        const sz = Math.max(8, Math.min(11, side / 3));
        g.append('text')
          .datum(leaf.data)
          .attr('class', 'voronoi-label')
          .attr('x', x).attr('y', y + sz / 3)
          .attr('font-size', sz)
          .text(d.code);
      }
    });

    // Hover tooltip
    cells
      .on('mouseenter', (ev, d) => {
        tooltip.innerHTML =
          `<span class="t-name">${d.data.name}</span>` +
          `<span class="t-code">(${d.data.code})</span>` +
          `<div class="t-rows">${d.data.value.toLocaleString()} rows</div>`;
        gsap.to(tooltip, { opacity: 1, duration: 0.12, overwrite: true });
      })
      .on('mousemove', (ev) => {
        const bb = container.getBoundingClientRect();
        tooltip.style.left = (ev.clientX - bb.left + 12) + 'px';
        tooltip.style.top  = (ev.clientY - bb.top  + 12) + 'px';
      })
      .on('mouseleave', () => {
        gsap.to(tooltip, { opacity: 0, duration: 0.1, overwrite: true });
      });

    // Click drill-down: highlight the clicked cell, dim the rest, surface a
    // language detail card below the treemap.
    let selectedCell = null;
    cells.on('click', function (ev, d) {
      const [cx, cy] = this._centroid;
      const sameAgain = selectedCell === this;
      if (sameAgain) {
        // reset
        selectedCell = null;
        cells.nodes().forEach(node => {
          const [ncx, ncy] = node._centroid;
          gsap.to(node, {
            scale: 1, opacity: 1,
            svgOrigin: `${ncx} ${ncy}`,
            filter: 'none',
            duration: 0.35, ease: 'power2.out', overwrite: 'auto',
          });
        });
        g.selectAll('.voronoi-label').each(function() {
          gsap.to(this, { opacity: 1, duration: 0.35, overwrite: 'auto' });
        });
        hideLanguageDetails();
        return;
      }
      selectedCell = this;
      cells.nodes().forEach(node => {
        const [ncx, ncy] = node._centroid;
        if (node === this) {
          gsap.to(node, {
            scale: 1.1, opacity: 1,
            svgOrigin: `${ncx} ${ncy}`,
            filter: 'drop-shadow(0 0 10px rgba(255,255,255,0.45)) brightness(1.35)',
            duration: 0.45, ease: 'power2.out', overwrite: 'auto',
          });
        } else {
          gsap.to(node, {
            scale: 1, opacity: 0,
            svgOrigin: `${ncx} ${ncy}`,
            filter: 'none',
            duration: 0.35, ease: 'power2.out', overwrite: 'auto',
          });
        }
      });
      g.selectAll('.voronoi-label').each(function(ld) {
        if (ld && ld.code === d.data.code) {
          gsap.to(this, { opacity: 1, duration: 0.45, overwrite: 'auto' });
        } else {
          gsap.to(this, { opacity: 0, duration: 0.35, overwrite: 'auto' });
        }
      });
      showLanguageDetails(d.data, colorScale(d.data.sizeValue));

      // Also emit the custom event so external code can react.
      container.dispatchEvent(new CustomEvent('voronoi-drilldown', {
        detail: { code: d.data.code, name: d.data.name, rows: d.data.value }
      }));
    });
  }

  draw();

  let t;
  window.addEventListener('resize', () => {
    clearTimeout(t);
    t = setTimeout(draw, 200);
  });
})();