fix(studio): address remaining caption designer feedback

Overlay: handle both per-word spans (generator output) and grouped text
nodes (existing templates). Wraps text nodes into individual spans on
demand so the overlay can target words in any caption format.

Property panel: add Typography (font, size, weight, spacing) and Color
(color, active, dim, opacity) sections alongside existing Position and
Transform controls.

Timeline: move caption timeline into a dedicated flex-shrink-0 section
below the main timeline tracks instead of inside the scrollable area.
Gives it fixed 60px height that's always visible.

Caption overrides: classify color tweens by comparing target color to
the dim baseline instead of relying on timeline position order. This
handles compositions with custom color tweens correctly.

App.tsx: remove polling interval, rely on runtime postMessage events
for caption detection. Add clarifying comment on why useEffect is
appropriate (external event subscription).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Vance Ingalls
2026-04-02 10:33:21 -07:00
co-authored by Claude Opus 4.6
parent a3c56e47e7
commit f8014f5e2a
5 changed files with 161 additions and 36 deletions
+18 -13
View File
@@ -83,25 +83,30 @@ export function applyCaptionOverrides(): void {
if (override.fontWeight !== undefined) styleProps.fontWeight = override.fontWeight;
if (override.fontFamily !== undefined) styleProps.fontFamily = override.fontFamily;
// Replace color values in existing GSAP tweens by timeline order.
// For any word, color tweens follow: dim (setup) → active (spoken) → after.
// Sort by startTime and assign by position, not by content heuristics.
// Replace color values in existing GSAP tweens.
// Instead of relying on timeline position order (fragile if custom
// color tweens exist), we classify each tween by comparing its
// target color to the current computed color of the element.
// Tweens that match the current color are "dim" tweens; tweens
// with a different color are "active" tweens.
if (override.activeColor || override.dimColor) {
const allTweens = gsap.getTweensOf(el);
const colorTweens = allTweens
.filter((tw) => tw.vars.color !== undefined)
.sort((a, b) => a.startTime() - b.startTime());
for (let i = 0; i < colorTweens.length; i++) {
if (i === 0 && override.dimColor) {
// First color tween = dim setup
colorTweens[i].vars.color = override.dimColor;
} else if (i === 1 && override.activeColor) {
// Second color tween = active/spoken
colorTweens[i].vars.color = override.activeColor;
} else if (i >= 2 && override.dimColor) {
// Third+ = after/deactivate (use dim color)
colorTweens[i].vars.color = override.dimColor;
// Use the first tween's color as the dim baseline — if no tweens,
// fall back to computed style.
const dimBaseline = colorTweens.length > 0 ? String(colorTweens[0].vars.color) : "";
for (const tw of colorTweens) {
const tweenColor = String(tw.vars.color);
if (tweenColor === dimBaseline) {
// This tween targets the dim/inactive color
if (override.dimColor) tw.vars.color = override.dimColor;
} else {
// This tween targets the active/spoken color
if (override.activeColor) tw.vars.color = override.activeColor;
}
}
+18 -18
View File
@@ -65,20 +65,18 @@ export function StudioApp() {
const [rightWidth, setRightWidth] = useState(400);
const [leftCollapsed, setLeftCollapsed] = useState(false);
const [rightCollapsed, setRightCollapsed] = useState(true);
// Auto-enter caption edit mode when viewing a captions composition
// Auto-enter caption edit mode when the iframe contains .caption-group elements.
// Listens for the runtime's postMessage events (state/timeline) which fire after
// all compositions are loaded, then checks for caption groups.
// This is a subscription to external events (postMessage from runtime) — useEffect
// is appropriate here. The runtime fires "state"/"timeline" messages after all
// compositions load, which triggers caption detection.
// eslint-disable-next-line no-restricted-syntax
useEffect(() => {
if (!projectId) return;
let pollId: ReturnType<typeof setInterval> | null = null;
let activating = false;
const tryActivateCaptions = () => {
if (useCaptionStore.getState().isEditMode || activating) {
if (pollId) { clearInterval(pollId); pollId = null; }
return;
}
@@ -88,7 +86,9 @@ export function StudioApp() {
try {
doc = iframe?.contentDocument ?? null;
win = iframe?.contentWindow ?? null;
} catch { return; }
} catch {
return;
}
if (!doc || !win) return;
const groups = doc.querySelectorAll(".caption-group");
@@ -102,7 +102,8 @@ export function StudioApp() {
// Strategy 1: data-composition-src or data-composition-file attributes
const compHosts = doc.querySelectorAll("[data-composition-src], [data-composition-file]");
for (const host of compHosts) {
const src = host.getAttribute("data-composition-src") || host.getAttribute("data-composition-file");
const src =
host.getAttribute("data-composition-src") || host.getAttribute("data-composition-file");
if (src && src.includes("captions")) {
captionSrcPath = src;
break;
@@ -154,7 +155,9 @@ export function StudioApp() {
captionSync.loadOverrides();
})
.catch(() => {})
.finally(() => { activating = false; });
.finally(() => {
activating = false;
});
};
// Listen for runtime messages that signal composition loading is complete
@@ -168,14 +171,11 @@ export function StudioApp() {
window.addEventListener("message", handleMessage);
// Try immediately in case compositions are already loaded
tryActivateCaptions();
// Poll until captions are detected — sub-composition scripts run async
pollId = setInterval(tryActivateCaptions, 200);
return () => {
window.removeEventListener("message", handleMessage);
if (pollId) clearInterval(pollId);
};
}, [activeCompPath, projectId, compIdToSrc]);
}, [activeCompPath, projectId, compIdToSrc, captionSync]);
// Auto-expand right panel when a caption word is selected
// eslint-disable-next-line no-restricted-syntax
@@ -296,7 +296,6 @@ export function StudioApp() {
const previewIframeRef = useRef<HTMLIFrameElement | null>(null);
const consoleErrorsRef = useRef<LintFinding[]>([]);
// Listen for external file changes (user editing HTML outside the editor).
// In dev: use Vite HMR. In embedded/production: use SSE from /api/events.
useMountEffect(() => {
@@ -850,14 +849,15 @@ export function StudioApp() {
});
}}
previewOverlay={
captionEditMode ? (
<CaptionOverlay iframeRef={previewIframeRef} />
) : undefined
captionEditMode ? <CaptionOverlay iframeRef={previewIframeRef} /> : undefined
}
timelineFooter={
captionEditMode ? (
<div className="border-t border-neutral-800/30">
<div className="flex items-center gap-1.5 px-2 py-1">
<div
className="border-t border-neutral-800/30 flex-shrink-0"
style={{ height: 60 }}
>
<div className="flex items-center gap-1.5 px-2 py-0.5">
<span className="text-[9px] font-medium text-neutral-500 uppercase tracking-wider">
Captions
</span>
@@ -51,7 +51,9 @@ function readWordBoxes(
if (!groupEl) continue;
const computed = win.getComputedStyle(groupEl);
if (parseFloat(computed.opacity) <= 0.01 || computed.visibility === "hidden") continue;
// Find word spans — may be direct children or inside wrappers
// Find word elements — handles both per-word spans (generator output)
// and grouped text nodes (existing caption templates that use
// el.textContent = line.text instead of individual word spans).
const resolvedWordEls: HTMLElement[] = [];
for (const child of groupEl.children) {
const c = child as HTMLElement;
@@ -62,6 +64,39 @@ function readWordBoxes(
resolvedWordEls.push(c);
}
}
// Fallback: if no word spans found but group has text content,
// the template uses grouped text. Wrap each word in a span so
// the overlay can target them individually.
if (resolvedWordEls.length === 0 && groupEl.textContent?.trim()) {
const textNode = groupEl.childNodes[0];
if (textNode && textNode.nodeType === Node.TEXT_NODE) {
const words = (textNode.textContent || "").split(/\s+/).filter(Boolean);
const frag = doc.createDocumentFragment();
for (const word of words) {
const span = doc.createElement("span");
span.textContent = word + " ";
span.style.display = "inline";
frag.appendChild(span);
resolvedWordEls.push(span);
}
groupEl.replaceChild(frag, textNode);
} else {
// Single span child with all text (e.g. vignelli template)
const singleSpan = groupEl.querySelector<HTMLElement>(":scope > span");
if (singleSpan && singleSpan.textContent?.trim()) {
const words = singleSpan.textContent.split(/\s+/).filter(Boolean);
const frag = doc.createDocumentFragment();
for (const word of words) {
const span = doc.createElement("span");
span.textContent = word + " ";
span.style.display = "inline";
frag.appendChild(span);
resolvedWordEls.push(span);
}
singleSpan.replaceWith(frag);
}
}
}
for (let wi = 0; wi < group.segmentIds.length; wi++) {
const segId = group.segmentIds[wi];
const wordEl = resolvedWordEls[wi] as HTMLElement | undefined;
@@ -179,6 +179,14 @@ export const CaptionPropertyPanel = memo(function CaptionPropertyPanel({
const y = effectiveStyle.y ?? 0;
const rotation = effectiveStyle.rotation ?? 0;
const scaleX = effectiveStyle.scaleX ?? 1;
const fontSize = effectiveStyle.fontSize ?? 48;
const fontWeight = effectiveStyle.fontWeight ?? 700;
const fontFamily = effectiveStyle.fontFamily ?? "Inter";
const color = effectiveStyle.color ?? "#ffffff";
const activeColor = effectiveStyle.activeColor ?? "#ffffff";
const dimColor = effectiveStyle.dimColor ?? "#999999";
const letterSpacing = effectiveStyle.letterSpacing ?? 0;
const opacity = effectiveStyle.opacity ?? 1;
// Count label
const countLabel = selectedSegmentIds.size === 1 ? "1 word" : `${selectedSegmentIds.size} words`;
@@ -222,9 +230,88 @@ export const CaptionPropertyPanel = memo(function CaptionPropertyPanel({
{/* Animation tab */}
{activeTab === "animation" && <CaptionAnimationPanel />}
{/* Style tab — Transform only */}
{/* Style tab */}
{activeTab === "style" && (
<div className="flex-1 overflow-y-auto px-3 py-2">
<Section label="Typography">
<Row label="Font">
<input
type="text"
value={fontFamily}
onChange={(e) => handleStyleChange({ fontFamily: e.target.value })}
className={inputCls}
/>
</Row>
<Row label="Size">
<input
type="number"
value={fontSize}
min={8}
step={1}
onChange={(e) => handleStyleChange({ fontSize: Number(e.target.value) })}
className={inputCls}
/>
</Row>
<Row label="Weight">
<input
type="number"
value={fontWeight}
min={100}
max={900}
step={100}
onChange={(e) => handleStyleChange({ fontWeight: Number(e.target.value) })}
className={inputCls}
/>
</Row>
<Row label="Spacing">
<input
type="number"
value={letterSpacing}
step={0.01}
onChange={(e) => handleStyleChange({ letterSpacing: Number(e.target.value) })}
className={inputCls}
/>
</Row>
</Section>
<Section label="Color">
<Row label="Color">
<input
type="color"
value={color}
onChange={(e) => handleStyleChange({ color: e.target.value })}
className={inputCls + " h-6 p-0.5 cursor-pointer"}
/>
</Row>
<Row label="Active">
<input
type="color"
value={activeColor}
onChange={(e) => handleStyleChange({ activeColor: e.target.value })}
className={inputCls + " h-6 p-0.5 cursor-pointer"}
/>
</Row>
<Row label="Dim">
<input
type="color"
value={dimColor}
onChange={(e) => handleStyleChange({ dimColor: e.target.value })}
className={inputCls + " h-6 p-0.5 cursor-pointer"}
/>
</Row>
<Row label="Opacity">
<input
type="number"
value={opacity}
min={0}
max={1}
step={0.1}
onChange={(e) => handleStyleChange({ opacity: Number(e.target.value) })}
className={inputCls}
/>
</Row>
</Section>
<Section label="Position">
<Row label="X">
<input
@@ -234,7 +321,6 @@ export const CaptionPropertyPanel = memo(function CaptionPropertyPanel({
className={inputCls}
/>
</Row>
<Row label="Y">
<input
type="number"
@@ -260,7 +346,6 @@ export const CaptionPropertyPanel = memo(function CaptionPropertyPanel({
className={inputCls}
/>
</Row>
<Row label="Rotation">
<input
type="number"
@@ -376,8 +376,8 @@ export const NLELayout = memo(function NLELayout({
onDrillDown={handleDrillDown}
renderClipContent={renderClipContent}
/>
{timelineFooter}
</div>
{timelineFooter && <div className="flex-shrink-0">{timelineFooter}</div>}
</div>
</>
)}