#version 450

// Original bits by Themaister
// Moire mitigation bits by Timothy Lottes, added by hunterk
 
layout(push_constant) uniform Push
{
   float BLOOM_STRENGTH;
   float OUTPUT_GAMMA;
   float CURVATURE;
   float moire_mitigation;
   float warpX;
   float warpY;
   float shadowMask;
   float maskDark;
   float maskLight;
} param;
 
#pragma parameter BLOOM_STRENGTH "Glow Strength" 0.45 0.0 0.8 0.05
#pragma parameter OUTPUT_GAMMA "Monitor Gamma" 2.2 1.8 2.6 0.02
#pragma parameter CURVATURE "Curvature" 0.0 0.0 1.0 1.0
#pragma parameter moire_mitigation "Moire:Noise Tradeoff" 4.0 1.0 10.0 1.0
#pragma parameter warpX "Curvature X-Axis" 0.031 0.0 0.125 0.01
#pragma parameter warpY "Curvature Y-Axis" 0.041 0.0 0.125 0.01
#pragma parameter shadowMask "Mask Effect" 0.0 0.0 4.0 1.0
#pragma parameter maskDark "maskDark" 0.5 0.0 2.0 0.1
#pragma parameter maskLight "maskLight" 1.5 0.0 2.0 0.1
 
#define iTime mod(float(global.FrameCount) / 60.0, 600.0)
#define fragCoord (vTexCoord.xy * global.OutputSize.xy)
 
layout(std140, set = 0, binding = 0) uniform UBO
{
    mat4 MVP;
    vec4 OutputSize;
    vec4 OriginalSize;
    vec4 SourceSize;
    vec4 CRTPassSize;
   uint FrameCount;
} 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;
}
 
#pragma stage fragment
layout(location = 0) in  vec2  vTexCoord;
layout(location = 0) out vec4  FragColor;
layout(set = 0, binding = 1) uniform sampler2D Source;
layout(set = 0, binding = 2) uniform sampler2D CRTPass;
 
// For debugging
#define BLOOM_ONLY 0
 
#define CRT_PASS CRTPass
 
// Convert from linear to sRGB.
//float Srgb(float c){return(c<0.0031308?c*12.92:1.055*pow(c,0.41666)-0.055);}
vec4 Srgb(vec4 c){return pow(c, vec4(1.0 / 2.2));}
 
// Convert from sRGB to linear.
//float Linear(float c){return(c<=0.04045)?c/12.92:pow((c+0.055)/1.055,2.4);}
float Linear(float c){return pow(c, 2.2);}
 
//
// Semi-Poor Quality Temporal Noise
//
 
// Base.
// Ripped ad modified from: https://www.shadertoy.com/view/4djSRW
float Noise(vec2 p,float x){p+=x;
 vec3 p3=fract(vec3(p.xyx)*10.1031);
 p3+=dot(p3,p3.yzx+19.19);
 return (fract((p3.x+p3.y)*p3.z)*2.0-1.0) / pow(2.0, 11.0 - param.moire_mitigation);}
 
// Step 1 in generation of the dither source texture.
float Noise1(vec2 uv,float n){
 float a=1.0,b=2.0,c=-12.0,t=1.0;  
 return (1.0/max(a*4.0+b*4.0,-c))*(
  Noise(uv+vec2(-1.0,-1.0)*t,n)*a+
  Noise(uv+vec2( 0.0,-1.0)*t,n)*b+
  Noise(uv+vec2( 1.0,-1.0)*t,n)*a+
  Noise(uv+vec2(-1.0, 0.0)*t,n)*b+
  Noise(uv+vec2( 0.0, 0.0)*t,n)*c+
  Noise(uv+vec2( 1.0, 0.0)*t,n)*b+
  Noise(uv+vec2(-1.0, 1.0)*t,n)*a+
  Noise(uv+vec2( 0.0, 1.0)*t,n)*b+
  Noise(uv+vec2( 1.0, 1.0)*t,n)*a+
 0.0);}
   
// Step 2 in generation of the dither source texture.
float Noise2(vec2 uv,float n){
 float a=1.0,b=2.0,c=-2.0,t=1.0;  
 return (1.0/(a*4.0+b*4.0))*(
  Noise1(uv+vec2(-1.0,-1.0)*t,n)*a+
  Noise1(uv+vec2( 0.0,-1.0)*t,n)*b+
  Noise1(uv+vec2( 1.0,-1.0)*t,n)*a+
  Noise1(uv+vec2(-1.0, 0.0)*t,n)*b+
  Noise1(uv+vec2( 0.0, 0.0)*t,n)*c+
  Noise1(uv+vec2( 1.0, 0.0)*t,n)*b+
  Noise1(uv+vec2(-1.0, 1.0)*t,n)*a+
  Noise1(uv+vec2( 0.0, 1.0)*t,n)*b+
  Noise1(uv+vec2( 1.0, 1.0)*t,n)*a+
 0.0);}
 
// Compute temporal dither from integer pixel position uv.
float Noise3(vec2 uv){return Noise2(uv,fract(iTime));}    
 
// Energy preserving dither, for {int pixel pos,color,amount}.
vec2 Noise4(vec2 uv,vec2 c,float a){
 // Grain value {-1 to 1}.
 vec2 g=vec2(Noise3(uv)*2.0);
 // Step size for black in non-linear space.
 float rcpStep=1.0/(256.0-1.0);
 // Estimate amount negative which still quantizes to zero.
 vec2 black=vec2(0.5*Linear(rcpStep));
 // Estimate amount above 1.0 which still quantizes to 1.0.
 vec2 white=vec2(2.0-Linear(1.0-rcpStep));
 // Add grain.
 return vec2(clamp(c+g*min(c+black,min(white-c,a)),0.0,1.0));}
 
//
// Pattern
//
 
// 4xMSAA pattern for quad given integer coordinates.
//
//  . x . . | < pixel
//  . . . x |
//  x . . .
//  . . x .
//
//  01
//  23
//
vec2 Quad4(vec2 pp){
 int q=(int(pp.x)&1)+((int(pp.y)&1)<<1);
 if(q==0)return pp+vec2( 0.25,-0.25);
 if(q==1)return pp+vec2( 0.25, 0.25);
 if(q==2)return pp+vec2(-0.25,-0.25);
         return pp+vec2(-0.25, 0.25);}
 
// Rotate {0.0,r} by a {-1.0 to 1.0}.
vec2 Rot(float r,float a){return vec2(r*cos(a*3.14159),r*sin(a*3.14159));}
 
//
// POOR QUALITY JITTERED
//
 
// Jittered position.
vec2 Jit(vec2 pp){
 // Start with better baseline pattern.
 pp=Quad4(pp);
 // Very poor quality (clumping) move in disc around pixel.
 float n=Noise(pp,fract(iTime));    
 float m=Noise(pp,fract(iTime*0.333))*0.5+0.5;
 m = sqrt(m) / 4.0;
 return pp+Rot(0.707*0.5*m,n);}
 
//
// POOR QUALITY JITTERED 4x
//
 
// Gaussian filtered jittered tap.
void JitGaus4(inout vec2 sumC,inout vec2 sumW,vec2 pp,vec2 mm){
 vec2 jj=Jit(pp);
 vec2 c=jj;
 vec2 vv=mm-jj;
 float w=exp2(-1.0*dot(vv,vv));    
 sumC+=c*vec2(w); sumW+=vec2(w);}  
 
// Many tap gaussian from poor quality jittered 4/sample per pixel
//
//  . x x x .
//  x x x x x
//  x x x x x
//  x x x x x
//  . x x x .
//
vec2 ResolveJitGaus4(vec2 pp){
 vec2 ppp=(pp);
 vec2 sumC=vec2(0.0);
 vec2 sumW=vec2(0.0);
 JitGaus4(sumC,sumW,ppp+vec2(-1.0,-2.0),pp);
 JitGaus4(sumC,sumW,ppp+vec2( 0.0,-2.0),pp);
 JitGaus4(sumC,sumW,ppp+vec2( 1.0,-2.0),pp);
 JitGaus4(sumC,sumW,ppp+vec2(-2.0,-1.0),pp);
 JitGaus4(sumC,sumW,ppp+vec2(-1.0,-1.0),pp);
 JitGaus4(sumC,sumW,ppp+vec2( 0.0,-1.0),pp);
 JitGaus4(sumC,sumW,ppp+vec2( 1.0,-1.0),pp);
 JitGaus4(sumC,sumW,ppp+vec2( 2.0,-1.0),pp);
 JitGaus4(sumC,sumW,ppp+vec2(-2.0, 0.0),pp);
 JitGaus4(sumC,sumW,ppp+vec2(-1.0, 0.0),pp);
 JitGaus4(sumC,sumW,ppp+vec2( 0.0, 0.0),pp);
 JitGaus4(sumC,sumW,ppp+vec2( 1.0, 0.0),pp);
 JitGaus4(sumC,sumW,ppp+vec2( 2.0, 0.0),pp);
 JitGaus4(sumC,sumW,ppp+vec2(-2.0, 1.0),pp);
 JitGaus4(sumC,sumW,ppp+vec2(-1.0, 1.0),pp);
 JitGaus4(sumC,sumW,ppp+vec2( 0.0, 1.0),pp);
 JitGaus4(sumC,sumW,ppp+vec2( 1.0, 1.0),pp);
 JitGaus4(sumC,sumW,ppp+vec2( 2.0, 1.0),pp);
 JitGaus4(sumC,sumW,ppp+vec2(-1.0, 2.0),pp);
 JitGaus4(sumC,sumW,ppp+vec2( 0.0, 2.0),pp);
 JitGaus4(sumC,sumW,ppp+vec2( 1.0, 2.0),pp);
 return sumC/sumW;}
 
vec2 moire_resolve(vec2 coord){
   vec2 pp = coord;
   vec2 cc = vec2(0.0, 0.0);
   
   cc = ResolveJitGaus4(pp);
   cc = Noise4(pp, cc, 1.0 / 32.0);
   cc = (param.CURVATURE < 0.5) ? pp : cc + vec2(0.0105, 0.015);
   
   return cc;
}
 
// 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 pp = moire_resolve(vTexCoord.xy);
   pp = (param.CURVATURE > 0.5) ? Warp(pp) : pp;
   
#if BLOOM_ONLY
    vec3 source = BLOOM_STRENGTH * texture(Source, pp).rgb;
#else
 
    vec3 source = 1.15 * texture(CRT_PASS, pp).rgb;
    vec3 bloom  = texture(Source, pp).rgb;
    source     += param.BLOOM_STRENGTH * bloom;
#endif
    FragColor = vec4(pow(clamp(source, 0.0, 1.0), vec3(1.0 / param.OUTPUT_GAMMA)), 1.0);
     /* TODO/FIXME - hacky clamp fix */
    if ( pp.x > 0.0106 && pp.x < 0.9999 && pp.y > 0.016 && pp.y < 0.9999)
        FragColor.rgb = FragColor.rgb;
    else
FragColor.rgb = vec3(0.0);
if (param.shadowMask > 0.0)
        FragColor.rgb = pow(pow(FragColor.rgb, vec3(2.2)) * Mask(vTexCoord.xy * global.OutputSize.xy * 1.000001), vec3(1.0 / 2.2));
}