//Pixel Shader for TEV stages
//3 TEV stages, 2 texgens, XXX IND stages
uniform sampler2D  samp0 : register(s0), samp1 : register(s1), samp2 : register(s2), samp3 : register(s3), samp4 : register(s4), samp5 : register(s5), samp6 : register(s6), samp7 : register(s7);

uniform float4 color[4] : register(c0);
uniform float4 k[4] : register(c4);
uniform float4 alphaRef[1] : register(c8);
uniform float4 texdim[8] : register(c9);
uniform float4 czbias[2] : register(c17);
uniform float4 cindscale[2] : register(c19);
uniform float4 cindmtx[6] : register(c21);
uniform float4 cfog[3] : register(c27);
void main(
  out float4 ocol0 : COLOR0,
  out float depth : DEPTH,
  in float4 rawpos : POSITION,
  in float4 colors_0 : COLOR0,
  in float4 colors_1 : COLOR1,
  in float3 uv0 : TEXCOORD0,
  in float3 uv1 : TEXCOORD1,
  in float4 clipPos : TEXCOORD2        ) {
  float4 c0 = color[1], c1 = color[2], c2 = color[3], prev = float4(0.0f, 0.0f, 0.0f, 0.0f), textemp = float4(0.0f, 0.0f, 0.0f, 0.0f), rastemp = float4(0.0f, 0.0f, 0.0f, 0.0f), konsttemp = float4(0.0f, 0.0f, 0.0f, 0.0f);
  float3 comp16 = float3(1.0f, 255.0f, 0.0f), comp24 = float3(1.0f, 255.0f, 255.0f*255.0f);
  float4 alphabump=float4(0.0f,0.0f,0.0f,0.0f);
  float3 tevcoord=float3(0.0f, 0.0f, 0.0f);
  float2 wrappedcoord=float2(0.0f,0.0f), tempcoord=float2(0.0f,0.0f);
  float4 cc0=float4(0.0f,0.0f,0.0f,0.0f), cc1=float4(0.0f,0.0f,0.0f,0.0f);
  float4 cc2=float4(0.0f,0.0f,0.0f,0.0f), cprev=float4(0.0f,0.0f,0.0f,0.0f);
  float4 crastemp=float4(0.0f,0.0f,0.0f,0.0f),ckonsttemp=float4(0.0f,0.0f,0.0f,0.0f);

clipPos = float4(rawpos.x, rawpos.y, clipPos.z, clipPos.w);
uv0.xy = uv0.xy * texdim[0].zw;
if (uv1.z)	uv1.xy = uv1.xy / uv1.z;
uv1.xy = uv1.xy * texdim[1].zw;
// TEV stage 0
rastemp = colors_0.rgba;
crastemp = frac(rastemp * (255.0f/256.0f)) * (256.0f/255.0f);
tevcoord.xy = uv0.xy;
textemp=tex2D(samp0,tevcoord.xy * texdim[0].xy).rgba;
// color combine
prev.rgb = saturate((textemp.rgb)*(crastemp.rgb));
// alpha combine
prev.a = saturate(crastemp.a*textemp.a);

// TEV done
// TEV stage 1
tevcoord.xy = uv1.xy;
textemp=tex2D(samp1,tevcoord.xy * texdim[1].xy).rgba;
konsttemp = float4(k[1].rrr, k[0].a);
ckonsttemp = frac(konsttemp * (255.0f/256.0f)) * (256.0f/255.0f);
// color combine
c2.rgb = saturate((textemp.rgb)+float3(1.0f, 1.0f, 1.0f)*(ckonsttemp.rgb));
// alpha combine
prev.a = prev.a+float4(0.0f, 0.0f, 0.0f, 0.0f).a;

// TEV done
// TEV stage 2
textemp = float4(1.0f, 1.0f, 1.0f, 1.0f);
konsttemp = float4(k[0].rgb, k[3].a);
ckonsttemp = frac(konsttemp * (255.0f/256.0f)) * (256.0f/255.0f);
cprev = frac(prev * (255.0f/256.0f)) * (256.0f/255.0f);
cc2 = frac(c2 * (255.0f/256.0f)) * (256.0f/255.0f);
// color combine
prev.rgb = saturate(4.0f*((c0.rgb)+lerp((ckonsttemp.rgb), (cc2.rgb), (cprev.rgb))));
// alpha combine
prev.a = ckonsttemp.a*cprev.a;

// TEV done
prev = frac(prev * (255.0f/256.0f)) * (256.0f/255.0f);
float zCoord = czbias[1].x + (clipPos.z / clipPos.w) * czbias[1].y;
depth = zCoord;
  float ze = cfog[1].x / (cfog[1].y - (zCoord / cfog[1].w));
  float x_adjust = (2.0f * (clipPos.x / cfog[2].y)) - 1.0f - cfog[2].x;
  x_adjust = sqrt(x_adjust * x_adjust + cfog[2].z * cfog[2].z) / cfog[2].z;
  ze *= x_adjust;
  float fog = saturate(ze - cfog[1].z);
  prev.rgb = lerp(prev.rgb,cfog[0].rgb,fog);
  ocol0 = prev;
}