Slug/
├── slug.hlsl          # Core fragment shader — coverage computation
├── band.hlsl          # Band-based optimization for glyph rendering
├── curve.hlsl         # Quadratic Bézier and line segment evaluation
├── README.md

git clone https://github.com/EricLengyel/Slug.git

#include "slug.hlsl"
#include "curve.hlsl"

// Line segment: p0, p1
// Quadratic Bézier: p0, p1 (control), p2

struct CurveRecord
{
    float2 p0;   // Start point
    float2 p1;   // Control point (or end point for lines)
    float2 p2;   // End point (unused for lines — flagged via type)
    // Type/flags encoded separately or in padding
};

// Inputs from vertex shader
struct PS_Input
{
    float4 position  : SV_Position;
    float2 glyphCoord : TEXCOORD0;  // Position in glyph/font units
    // Band index or precomputed band data
    nointerpolation uint bandOffset : TEXCOORD1;
    nointerpolation uint curveCount : TEXCOORD2;
};

// Glyph curve data buffer
StructuredBuffer<float4> CurveBuffer : register(t0);

float4 PS_Slug(PS_Input input) : SV_Target
{
    float coverage = ComputeGlyphCoverage(
        input.glyphCoord,
        CurveBuffer,
        input.bandOffset,
        input.curveCount
    );

    // Premultiplied alpha output
    float4 color = float4(textColor.rgb * coverage, coverage);
    return color;
}

// Evaluate whether a quadratic bezier contributes to coverage at point p
// p0: start, p1: control, p2: end
// Returns signed coverage contribution
float QuadraticBezierCoverage(float2 p, float2 p0, float2 p1, float2 p2)
{
    // Transform to canonical space
    float2 a = p1 - p0;
    float2 b = p0 - 2.0 * p1 + p2;

    // Find t values where bezier Y == p.y
    float2 delta = p - p0;
    
    float A = b.y;
    float B = a.y;
    float C = p0.y - p.y;

    float coverage = 0.0;

    if (abs(A) > 1e-6)
    {
        float disc = B * B - A * C;
        if (disc >= 0.0)
        {
            float sqrtDisc = sqrt(disc);
            float t0 = (-B - sqrtDisc) / A;
            float t1 = (-B + sqrtDisc) / A;

            // For each valid t in [0,1], compute x and check winding
            if (t0 >= 0.0 && t0 <= 1.0)
            {
                float x = (A * t0 + 2.0 * B) * t0 + p0.x + delta.x;
                // ... accumulate signed coverage
            }
            if (t1 >= 0.0 && t1 <= 1.0)
            {
                float x = (A * t1 + 2.0 * B) * t1 + p0.x + delta.x;
                // ... accumulate signed coverage
            }
        }
    }
    else
    {
        // Degenerate to linear case
        float t = -C / (2.0 * B);
        if (t >= 0.0 && t <= 1.0)
        {
            float x = 2.0 * a.x * t + p0.x;
            // ... accumulate signed coverage
        }
    }

    return coverage;
}

// Signed coverage contribution of a line segment from p0 to p1
float LineCoverage(float2 p, float2 p0, float2 p1)
{
    // Check Y range
    float minY = min(p0.y, p1.y);
    float maxY = max(p0.y, p1.y);

    if (p.y < minY || p.y >= maxY)
        return 0.0;

    // Interpolate X at p.y
    float t = (p.y - p0.y) / (p1.y - p0.y);
    float x = lerp(p0.x, p1.x, t);

    // Winding: +1 if p is to the left (inside), -1 if right
    float dir = (p1.y > p0.y) ? 1.0 : -1.0;
    return (p.x <= x) ? dir : 0.0;
}

// Compute AA coverage using partial pixel coverage
// windingNumber: integer winding from coverage pass
// distToEdge: signed distance to nearest curve (in pixels)
float AntiAliasedCoverage(int windingNumber, float distToEdge)
{
    // Non-zero winding rule
    bool inside = (windingNumber != 0);
    
    // Smooth transition at edges using clamp
    float edgeCoverage = clamp(distToEdge + 0.5, 0.0, 1.0);
    
    return inside ? edgeCoverage : (1.0 - edgeCoverage);
}

struct VS_Input
{
    float2 position   : POSITION;     // Glyph quad corner in screen/world space
    float2 glyphCoord : TEXCOORD0;    // Corresponding glyph-space coordinate
    uint   bandOffset : TEXCOORD1;    // Offset into curve buffer for this glyph
    uint   curveCount : TEXCOORD2;    // Number of curves in band
};

struct VS_Output
{
    float4 position   : SV_Position;
    float2 glyphCoord : TEXCOORD0;
    nointerpolation uint bandOffset : TEXCOORD1;
    nointerpolation uint curveCount : TEXCOORD2;
};

VS_Output VS_Slug(VS_Input input)
{
    VS_Output output;
    output.position   = mul(float4(input.position, 0.0, 1.0), WorldViewProjection);
    output.glyphCoord = input.glyphCoord;
    output.bandOffset = input.bandOffset;
    output.curveCount = input.curveCount;
    return output;
}

// 1. Load font file and extract glyph outlines
FontOutline outline = LoadGlyphOutline(font, glyphIndex);

// 2. Decompose to quadratic Beziers (TrueType is already quadratic)
//    OTF cubic curves must be approximated/split into quadratics
std::vector<SlugCurve> curves = DecomposeToQuadratics(outline);

// 3. Compute bands
float bandHeight = outline.bounds.height / NUM_BANDS;
std::vector<BandData> bands = ComputeBands(curves, NUM_BANDS, bandHeight);

// 4. Upload to GPU
UploadStructuredBuffer(curveBuffer, curves.data(), curves.size());
UploadStructuredBuffer(bandBuffer, bands.data(), bands.size());

// 5. Per glyph instance: store bandOffset and curveCount per band
//    in vertex data so the fragment shader can index directly

// Blend state: premultiplied alpha
BlendState SlugBlend
{
    BlendEnable    = TRUE;
    SrcBlend       = ONE;           // Premultiplied
    DestBlend      = INV_SRC_ALPHA;
    BlendOp        = ADD;
    SrcBlendAlpha  = ONE;
    DestBlendAlpha = INV_SRC_ALPHA;
    BlendOpAlpha   = ADD;
};

// Depth: typically write disabled for text overlay
DepthStencilState SlugDepth
{
    DepthEnable    = FALSE;
    DepthWriteMask = ZERO;
};

// Rasterizer: no backface culling (glyph quads are 2D)
RasterizerState SlugRaster
{
    CullMode = NONE;
    FillMode = SOLID;
};

// For each glyph in string:
for (auto& glyph : string.glyphs)
{
    // Emit a quad (2 triangles) covering the glyph bounding box
    // Each vertex carries:
    //   - screen position
    //   - glyph-space coordinate (the same corner in font units)
    //   - bandOffset + curveCount for the fragment shader

    float2 min = glyph.screenMin;
    float2 max = glyph.screenMax;
    float2 glyphMin = glyph.fontMin;
    float2 glyphMax = glyph.fontMax;

    EmitQuad(min, max, glyphMin, glyphMax,
             glyph.bandOffset, glyph.curveCount);
}

float scale = desiredPixelSize / font.unitsPerEm;
float2 screenMin = origin + glyph.fontMin * scale;
float2 screenMax = origin + glyph.fontMax * scale;