/*
    FSR - [RCAS] ROBUST CONTRAST ADAPTIVE SHARPENING
    Ported from https://www.shadertoy.com/view/stXSWB, MIT license
*/

#pragma parameter FSR_SHARPENING "FSR RCAS Sharpening Amount (Lower = Sharper)" 0.6 0.0 2.0 0.1

#if defined(VERTEX)

#if __VERSION__ >= 130
#define COMPAT_VARYING out
#define COMPAT_ATTRIBUTE in
#define COMPAT_TEXTURE texture
#else
#define COMPAT_VARYING varying 
#define COMPAT_ATTRIBUTE attribute 
#define COMPAT_TEXTURE texture2D
#endif

#ifdef GL_ES
#define COMPAT_PRECISION mediump
#else
#define COMPAT_PRECISION
#endif

COMPAT_ATTRIBUTE vec4 VertexCoord;
COMPAT_ATTRIBUTE vec4 COLOR;
COMPAT_ATTRIBUTE vec4 TexCoord;
COMPAT_VARYING vec4 COL0;
COMPAT_VARYING vec4 TEX0;

uniform mat4 MVPMatrix;
uniform COMPAT_PRECISION int FrameDirection;
uniform COMPAT_PRECISION int FrameCount;
uniform COMPAT_PRECISION vec2 OutputSize;
uniform COMPAT_PRECISION vec2 TextureSize;
uniform COMPAT_PRECISION vec2 InputSize;

void main()
{
    gl_Position = MVPMatrix * VertexCoord;
    COL0 = COLOR;
    TEX0.xy = TexCoord.xy;
}

#elif defined(FRAGMENT)

#if __VERSION__ >= 130
#define COMPAT_VARYING in
#define COMPAT_TEXTURE texture
out vec4 FragColor;
#else
#define COMPAT_VARYING varying
#define FragColor gl_FragColor
#define COMPAT_TEXTURE texture2D
#endif

#ifdef GL_ES
#ifdef GL_FRAGMENT_PRECISION_HIGH
precision highp float;
#else
precision mediump float;
#endif
#define COMPAT_PRECISION mediump
#else
#define COMPAT_PRECISION
#endif

uniform COMPAT_PRECISION int FrameDirection;
uniform COMPAT_PRECISION int FrameCount;
uniform COMPAT_PRECISION vec2 OutputSize;
uniform COMPAT_PRECISION vec2 TextureSize;
uniform COMPAT_PRECISION vec2 InputSize;
uniform sampler2D Texture;
COMPAT_VARYING vec4 TEX0;

// compatibility #defines
#define Source Texture
#define vTexCoord TEX0.xy

#define SourceSize vec4(TextureSize, 1.0 / TextureSize) //either TextureSize or InputSize
#define outsize vec4(OutputSize, 1.0 / OutputSize)

#ifdef PARAMETER_UNIFORM
uniform COMPAT_PRECISION float FSR_SHARPENING;
#else
#define FSR_SHARPENING 0.6
#endif

#define FSR_RCAS_LIMIT (0.25-(1.0/16.0))
//#define FSR_RCAS_DENOISE

// Input callback prototypes that need to be implemented by calling shader
vec4 FsrRcasLoadF(vec2 p);
//------------------------------------------------------------------------------------------------------------------------------
void FsrRcasCon(
    out float con,
    // The scale is {0.0 := maximum, to N>0, where N is the number of stops (halving) of the reduction of sharpness}.
    float sharpness
){
    // Transform from stops to linear value.
    con = exp2(-sharpness);
}

vec3 FsrRcasF(
    vec2 ip, // Integer pixel position in output.
    float con
)
{
    // Constant generated by RcasSetup().
    // Algorithm uses minimal 3x3 pixel neighborhood.
    //    b 
    //  d e f
    //    h
    vec2 sp = vec2(ip);
    vec3 b = FsrRcasLoadF(sp + vec2( 0,-1)).rgb;
    vec3 d = FsrRcasLoadF(sp + vec2(-1, 0)).rgb;
    vec3 e = FsrRcasLoadF(sp).rgb;
    vec3 f = FsrRcasLoadF(sp+vec2( 1, 0)).rgb;
    vec3 h = FsrRcasLoadF(sp+vec2( 0, 1)).rgb;
    // Luma times 2.
    float bL = b.g + .5 * (b.b + b.r);
    float dL = d.g + .5 * (d.b + d.r);
    float eL = e.g + .5 * (e.b + e.r);
    float fL = f.g + .5 * (f.b + f.r);
    float hL = h.g + .5 * (h.b + h.r);
    // Noise detection.
    float nz = .25 * (bL + dL + fL + hL) - eL;
    nz=clamp(
        abs(nz)
        /(
            max(max(bL,dL),max(eL,max(fL,hL)))
            -min(min(bL,dL),min(eL,min(fL,hL)))
        ),
        0., 1.
    );
    nz=1.-.5*nz;
    // Min and max of ring.
    vec3 mn4 = min(b, min(f, h));
    vec3 mx4 = max(b, max(f, h));
    // Immediate constants for peak range.
    vec2 peakC = vec2(1., -4.);
    // Limiters, these need to be high precision RCPs.
    vec3 hitMin = mn4 / (4. * mx4);
    vec3 hitMax = (peakC.x - mx4) / (4.* mn4 + peakC.y);
    vec3 lobeRGB = max(-hitMin, hitMax);
    float lobe = max(
        -FSR_RCAS_LIMIT,
        min(max(lobeRGB.r, max(lobeRGB.g, lobeRGB.b)), 0.)
    )*con;
    // Apply noise removal.
    #ifdef FSR_RCAS_DENOISE
    lobe *= nz;
    #endif
    // Resolve, which needs the medium precision rcp approximation to avoid visible tonality changes.
    return (lobe * (b + d + h + f) + e) / (4. * lobe + 1.);
} 


vec4 FsrRcasLoadF(vec2 p) {
    return COMPAT_TEXTURE(Source,p/OutputSize.xy);
}

void main()
{
    vec2 fragCoord = vTexCoord.xy * OutputSize.xy;
    
    // Set up constants
    float con;
    FsrRcasCon(con, FSR_SHARPENING);

    // Perform RCAS pass
    vec3 col = FsrRcasF(fragCoord, con);

    FragColor = vec4(col,1);
}

#endif