perf(text): cache shaped runs in ShapeText (#52)

ShapeText re-decoded UTF-8, re-looked-up every glyph, and recomputed
layout every frame for static strings (DrawText / EmitCenteredLabel run
inside per-frame onBuild). DrawText and EmitCenteredLabel also did a
second full pass over the glyphs to apply alignment.

Memoize the shaped run, keyed by (Font*, pxSize, color, utf8), as an
origin-relative vector<GlyphItem>. A cache hit skips decode/lookup/layout
and just translates the cached run into the output buffer by
(x + alignShift, baselineY). The alignment shift (Center = -advance/2,
Right = -advance) is folded into ShapeText's single pass, dropping the
second loop in both callers. TextAlign moves to the :UI partition so
ShapeText can take it.

Pure CPU memoization — the glyph buffer is fully rewritten and re-flushed
every frame, so a hit is byte-equivalent. A miss still calls Ensure so new
glyphs rasterise and dirty the atlas; hits don't (atlas entries are never
evicted). InvalidateFont drops a font's runs before it is destroyed (the
cache, like FontAtlas's glyph cache, keys on the Font pointer). A soft cap
bounds memory against pathological per-frame-unique text.

Adds the ShapeTextCache test (15 checks): hit == miss byte-for-byte, hits
don't touch the atlas, translate/alignment/truncation/InvalidateFont.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
catbot 2026-06-16 15:40:52 +00:00
commit ca48f79465
7 changed files with 391 additions and 40 deletions

View file

@ -48,39 +48,79 @@ std::uint32_t UIRenderer::ShapeText(Font& font, float pxSize,
std::string_view utf8,
std::array<float,4> color,
GlyphItem* out, std::uint32_t outCapacity,
float* outAdvance) {
float* outAdvance,
TextAlign align) {
if (fontAtlas == nullptr) {
std::println("UIRenderer::ShapeText: no FontAtlas (set fontAtlas before Initialize)");
std::abort();
}
const float scale = pxSize / FontAtlas::kBaseSize;
float cursor = x;
std::uint32_t written = 0;
// Look up (or build) the origin-relative shaped run. It is stored with
// the pen starting at x=0, baseline=0 so a cache hit only needs the
// translate below. The whole string is shaped (no outCapacity limit) so
// a later call with a larger buffer still gets the full run.
ShapedRunKey key{&font, pxSize, color, std::string(utf8)};
auto it = shapedRuns_.find(key);
if (it == shapedRuns_.end()) {
// Miss: shape from scratch. Ensure() each glyph so brand-new ones
// rasterise into the atlas and mark it dirty for the next upload —
// a hit skips this, which is safe because atlas entries are never
// evicted once placed.
const float scale = pxSize / FontAtlas::kBaseSize;
ShapedRun run;
float cursor = 0.0f;
std::size_t i = 0;
while (i < utf8.size()) {
std::uint32_t cp = DecodeUtf8(utf8, i);
if (cp == 0) break;
if (cp == '\n') { continue; }
std::size_t i = 0;
while (i < utf8.size() && written < outCapacity) {
std::uint32_t cp = DecodeUtf8(utf8, i);
if (cp == 0) break;
if (cp == '\n') { continue; }
fontAtlas->Ensure(font, cp);
const Glyph* g = fontAtlas->Lookup(font, cp);
if (g == nullptr) continue;
fontAtlas->Ensure(font, cp);
const Glyph* g = fontAtlas->Lookup(font, cp);
if (g == nullptr) continue;
if (g->w > 0 && g->h > 0) {
GlyphItem& gi = out[written++];
gi.x = cursor + g->xoff * scale;
gi.y = baselineY + g->yoff * scale;
gi.w = g->w * scale;
gi.h = g->h * scale;
gi.u0 = g->u0; gi.v0 = g->v0;
gi.u1 = g->u1; gi.v1 = g->v1;
gi.r = color[0]; gi.g = color[1]; gi.b = color[2]; gi.a = color[3];
if (g->w > 0 && g->h > 0) {
GlyphItem gi;
gi.x = cursor + g->xoff * scale;
gi.y = g->yoff * scale;
gi.w = g->w * scale;
gi.h = g->h * scale;
gi.u0 = g->u0; gi.v0 = g->v0;
gi.u1 = g->u1; gi.v1 = g->v1;
gi.r = color[0]; gi.g = color[1]; gi.b = color[2]; gi.a = color[3];
run.glyphs.push_back(gi);
}
cursor += g->advance * scale;
}
cursor += g->advance * scale;
run.advance = cursor;
if (shapedRuns_.size() >= kMaxShapedRuns) shapedRuns_.clear();
it = shapedRuns_.emplace(std::move(key), std::move(run)).first;
}
if (outAdvance) *outAdvance = cursor - x;
const ShapedRun& run = it->second;
if (outAdvance) *outAdvance = run.advance;
// Fold the alignment shift into the translate so callers don't need a
// second pass over the glyphs.
const float alignShift = (align == TextAlign::Center) ? -run.advance * 0.5f
: (align == TextAlign::Right) ? -run.advance
: 0.0f;
const float tx = x + alignShift;
std::uint32_t written = 0;
for (const GlyphItem& src : run.glyphs) {
if (written >= outCapacity) break;
GlyphItem& gi = out[written++];
gi = src;
gi.x += tx;
gi.y += baselineY;
}
return written;
}
void UIRenderer::InvalidateFont(const Font& font) noexcept {
std::erase_if(shapedRuns_, [&font](const auto& kv) {
return kv.first.font == &font;
});
}