#version 450

layout(push_constant) uniform Push
{
    float hardScan;
    float hardPix;
    float warpX;
    float warpY;
    float maskDark;
    float maskLight;
    float scaleInLinearGamma;
    float shadowMask;
    float brightBoost;
    float hardBloomScan;
    float hardBloomPix;
    float bloomAmount;
    float shape;
} param;

#pragma parameter hardScan "hardScan" -8.0 -20.0 0.0 1.0
#pragma parameter hardPix "hardPix" -3.0 -20.0 0.0 1.0
#pragma parameter warpX "warpX" 0.031 0.0 0.125 0.01
#pragma parameter warpY "warpY" 0.041 0.0 0.125 0.01
#pragma parameter maskDark "maskDark" 0.5 0.0 2.0 0.1
#pragma parameter maskLight "maskLight" 1.5 0.0 2.0 0.1
#pragma parameter scaleInLinearGamma "scaleInLinearGamma" 1.0 0.0 1.0 1.0
#pragma parameter shadowMask "shadowMask" 3.0 0.0 4.0 1.0
#pragma parameter brightBoost "brightness boost" 1.0 0.0 2.0 0.05
#pragma parameter hardBloomPix "bloom-x soft" -1.5 -2.0 -0.5 0.1
#pragma parameter hardBloomScan "bloom-y soft" -2.0 -4.0 -1.0 0.1
#pragma parameter bloomAmount "bloom amount" 0.4 0.0 1.0 0.05
#pragma parameter shape "filter kernel shape" 2.0 0.0 10.0 0.05

layout(std140, set = 0, binding = 0) uniform UBO
{
   mat4 MVP;
   vec4 OutputSize;
   vec4 OriginalSize;
   vec4 SourceSize;
} global;

#pragma stage vertex
layout(location = 0) in vec4 Position;
layout(location = 1) in vec2 TexCoord;
layout(location = 0) out vec2 vTexCoord;

void main()
{
    gl_Position = global.MVP * Position;
    vTexCoord = TexCoord;
}

// PUBLIC DOMAIN CRT STYLED SCAN-LINE SHADER
//
//   by Timothy Lottes
//
// This is more along the style of a really good CGA arcade monitor.
// With RGB inputs instead of NTSC.
// The shadow mask example has the mask rotated 90 degrees for less chromatic aberration.
//
// Left it unoptimized to show the theory behind the algorithm.
//
// It is an example what I personally would want as a display option for pixel art games.
// Please take and use, change, or whatever.

#pragma stage fragment
layout(location = 0) in vec2 vTexCoord;
layout(location = 1) in vec2 FragCoord;
layout(location = 0) out vec4 FragColor;
layout(set = 0, binding = 2) uniform sampler2D Source;
layout(set = 0, binding = 3) uniform sampler2D ORIG_LINEARIZED;

//Uncomment to reduce instructions with simpler linearization
//(fixes HD3000 Sandy Bridge IGP)
#define SIMPLE_LINEAR_GAMMA
#define DO_BLOOM 1

// ------------- //

// sRGB to Linear.
// Assuming using sRGB typed textures this should not be needed.
#ifdef SIMPLE_LINEAR_GAMMA
float ToLinear1(float c)
{
    return c;
}
vec3 ToLinear(vec3 c)
{
    return c;
}
vec3 ToSrgb(vec3 c)
{
    return pow(c, vec3(1.0 / 2.2));
}
#else
float ToLinear1(float c)
{
    if (param.scaleInLinearGamma == 0) 
        return c;
    
    return(c<=0.04045) ? c/12.92 : pow((c + 0.055)/1.055, 2.4);
}

vec3 ToLinear(vec3 c)
{
    if (param.scaleInLinearGamma==0) 
        return c;
    
    return vec3(ToLinear1(c.r), ToLinear1(c.g), ToLinear1(c.b));
}

// Linear to sRGB.
// Assuming using sRGB typed textures this should not be needed.
float ToSrgb1(float c)
{
    if (param.scaleInLinearGamma == 0) 
        return c;
    
    return(c<0.0031308 ? c*12.92 : 1.055*pow(c, 0.41666) - 0.055);
}

vec3 ToSrgb(vec3 c)
{
    if (param.scaleInLinearGamma == 0) 
        return c;
    
    return vec3(ToSrgb1(c.r), ToSrgb1(c.g), ToSrgb1(c.b));
}
#endif



// Nearest emulated sample given floating point position and texel offset.
// Also zero's off screen.
vec3 Fetch(vec2 pos,vec2 off){
  pos=(floor(pos*global.SourceSize.xy+off)+vec2(0.5,0.5))/global.SourceSize.xy;
#ifdef SIMPLE_LINEAR_GAMMA
  return ToLinear(param.brightBoost * (texture(ORIG_LINEARIZED,pos.xy).rgb));
#else
  return ToLinear(param.brightBoost * texture(ORIG_LINEARIZED,pos.xy).rgb);
#endif
}
  
// Distance in emulated pixels to nearest texel.
vec2 Dist(vec2 pos)
{
    pos = pos*global.SourceSize.xy;
    
    return -((pos - floor(pos)) - vec2(0.5));
}
    
// 1D Gaussian.
float Gaus(float pos, float scale)
{
    return exp2(scale*pow(abs(pos), param.shape));
}

// 3-tap Gaussian filter along horz line.
vec3 Horz3(vec2 pos, float off)
{
    vec3 b    = Fetch(pos, vec2(-1.0, off));
    vec3 c    = Fetch(pos, vec2( 0.0, off));
    vec3 d    = Fetch(pos, vec2( 1.0, off));
    float dst = Dist(pos).x;

    // Convert distance to weight.
    float scale = param.hardPix;
    float wb = Gaus(dst-1.0,scale);
    float wc = Gaus(dst+0.0,scale);
    float wd = Gaus(dst+1.0,scale);

    // Return filtered sample.
    return (b*wb+c*wc+d*wd)/(wb+wc+wd);
}

// 5-tap Gaussian filter along horz line.
vec3 Horz5(vec2 pos,float off){
    vec3 a = Fetch(pos,vec2(-2.0, off));
    vec3 b = Fetch(pos,vec2(-1.0, off));
    vec3 c = Fetch(pos,vec2( 0.0, off));
    vec3 d = Fetch(pos,vec2( 1.0, off));
    vec3 e = Fetch(pos,vec2( 2.0, off));
    
    float dst = Dist(pos).x;
    // Convert distance to weight.
    float scale = param.hardPix;
    float wa = Gaus(dst - 2.0, scale);
    float wb = Gaus(dst - 1.0, scale);
    float wc = Gaus(dst + 0.0, scale);
    float wd = Gaus(dst + 1.0, scale);
    float we = Gaus(dst + 2.0, scale);
    
    // Return filtered sample.
    return (a*wa+b*wb+c*wc+d*wd+e*we)/(wa+wb+wc+wd+we);
}
  
// 7-tap Gaussian filter along horz line.
vec3 Horz7(vec2 pos,float off)
{
    vec3 a = Fetch(pos, vec2(-3.0, off));
    vec3 b = Fetch(pos, vec2(-2.0, off));
    vec3 c = Fetch(pos, vec2(-1.0, off));
    vec3 d = Fetch(pos, vec2( 0.0, off));
    vec3 e = Fetch(pos, vec2( 1.0, off));
    vec3 f = Fetch(pos, vec2( 2.0, off));
    vec3 g = Fetch(pos, vec2( 3.0, off));

    float dst = Dist(pos).x;
    // Convert distance to weight.
    float scale = param.hardBloomPix;
    float wa = Gaus(dst - 3.0, scale);
    float wb = Gaus(dst - 2.0, scale);
    float wc = Gaus(dst - 1.0, scale);
    float wd = Gaus(dst + 0.0, scale);
    float we = Gaus(dst + 1.0, scale);
    float wf = Gaus(dst + 2.0, scale);
    float wg = Gaus(dst + 3.0, scale);

    // Return filtered sample.
    return (a*wa+b*wb+c*wc+d*wd+e*we+f*wf+g*wg)/(wa+wb+wc+wd+we+wf+wg);
}
  
// Return scanline weight.
float Scan(vec2 pos, float off)
{
    float dst = Dist(pos).y;

    return Gaus(dst + off, param.hardScan);
}
  
// Return scanline weight for bloom.
float BloomScan(vec2 pos, float off)
{
    float dst = Dist(pos).y;
    
    return Gaus(dst + off, param.hardBloomScan);
}

// Allow nearest three lines to effect pixel.
vec3 Tri(vec2 pos)
{
    vec3 a = Horz3(pos,-1.0);
    vec3 b = Horz5(pos, 0.0);
    vec3 c = Horz3(pos, 1.0);
    
    float wa = Scan(pos,-1.0); 
    float wb = Scan(pos, 0.0);
    float wc = Scan(pos, 1.0);
    
    return a*wa + b*wb + c*wc;
}
  
// Small bloom.
vec3 Bloom(vec2 pos)
{
    vec3 a = Horz5(pos,-2.0);
    vec3 b = Horz7(pos,-1.0);
    vec3 c = Horz7(pos, 0.0);
    vec3 d = Horz7(pos, 1.0);
    vec3 e = Horz5(pos, 2.0);

    float wa = BloomScan(pos,-2.0);
    float wb = BloomScan(pos,-1.0); 
    float wc = BloomScan(pos, 0.0);
    float wd = BloomScan(pos, 1.0);
    float we = BloomScan(pos, 2.0);

    return a*wa+b*wb+c*wc+d*wd+e*we;
}
  
// Distortion of scanlines, and end of screen alpha.
vec2 Warp(vec2 pos)
{
    pos  = pos*2.0-1.0;    
    pos *= vec2(1.0 + (pos.y*pos.y)*param.warpX, 1.0 + (pos.x*pos.x)*param.warpY);
    
    return pos*0.5 + 0.5;
}
  
// Shadow mask.
vec3 Mask(vec2 pos)
{
    vec3 mask = vec3(param.maskDark, param.maskDark, param.maskDark);
  
    // Very compressed TV style shadow mask.
    if (param.shadowMask == 1.0) 
    {
        float line = param.maskLight;
        float odd = 0.0;
        
        if (fract(pos.x*0.166666666) < 0.5) odd = 1.0;
        if (fract((pos.y + odd) * 0.5) < 0.5) line = param.maskDark;  
        
        pos.x = fract(pos.x*0.333333333);

        if      (pos.x < 0.333) mask.r = param.maskLight;
        else if (pos.x < 0.666) mask.g = param.maskLight;
        else                    mask.b = param.maskLight;
        mask*=line;  
    } 

    // Aperture-grille.
    else if (param.shadowMask == 2.0) 
    {
        pos.x = fract(pos.x*0.333333333);

        if      (pos.x < 0.333) mask.r = param.maskLight;
        else if (pos.x < 0.666) mask.g = param.maskLight;
        else                    mask.b = param.maskLight;
    } 

    // Stretched VGA style shadow mask (same as prior shaders).
    else if (param.shadowMask == 3.0) 
    {
        pos.x += pos.y*3.0;
        pos.x  = fract(pos.x*0.166666666);

        if      (pos.x < 0.333) mask.r = param.maskLight;
        else if (pos.x < 0.666) mask.g = param.maskLight;
        else                    mask.b = param.maskLight;
    }

    // VGA style shadow mask.
    else if (param.shadowMask == 4.0) 
    {
        pos.xy  = floor(pos.xy*vec2(1.0, 0.5));
        pos.x  += pos.y*3.0;
        pos.x   = fract(pos.x*0.166666666);

        if      (pos.x < 0.333) mask.r = param.maskLight;
        else if (pos.x < 0.666) mask.g = param.maskLight;
        else                    mask.b = param.maskLight;
    }

    return mask;
}

void main()
{
    vec2 pos = vTexCoord;

    FragColor = vec4(Bloom(pos)*param.bloomAmount, 1.0);
}