acdream/src/AcDream.App/Rendering/PortalDepthMaskRenderer.cs

using System;
using System.Numerics;
using Silk.NET.OpenGL;

namespace AcDream.App.Rendering;

/// <summary>
/// BR-2 (holistic building-render port): retail's invisible portal depth
/// writes — the port of <c>D3DPolyRender::DrawPortalPolyInternal</c>
/// (Ghidra 0x0059bc90, pc:424490).
///
/// <para>Retail projects a portal polygon, software-clips it against the
/// installed portal view (<c>polyClipFinish</c>), and draws the survivor as a
/// COLOR-INVISIBLE triangle fan with depth-test ALWAYS + depth-write ON:</para>
/// <list type="bullet">
///   <item><b>Seal</b> (retail <c>maxZ2=6</c>, bit0 clear, data 0x00820e14):
///   z = the polygon's true projected depth. Drawn on portals leading OUTSIDE
///   (<c>other_cell_id==0xFFFF</c>) after the landscape pass — terrain seen
///   through a doorway keeps its pixels because farther interior geometry
///   z-fails inside the aperture (PView::DrawCells loop 1, Ghidra 0x005a4840,
///   pc:432783-432786).</item>
///   <item><b>Punch</b> (retail <c>maxZ1=7</c>, bit0 set, data 0x00820e18):
///   z forced to the far plane (0.99999988) — erases depth inside a building
///   aperture so the interior cells drawn next land cleanly
///   (ConstructView(CBldPortal) mode-1, pc:433827). BR-2 commit 2 wires this
///   side.</item>
/// </list>
///
/// <para>Where retail clips the polygon on the CPU against the view, we apply
/// the SAME view region via <c>gl_ClipDistance</c> from the slice's clip-space
/// half-planes (≤8, the validated <see cref="ClipPlaneSet"/> output) — the
/// depth write lands only inside the slice region, matching retail's clipped
/// fan.</para>
///
/// <para>Self-contained GL state (feedback_render_self_contained_gl_state):
/// sets everything it depends on, restores the frame-global convention on
/// exit, no early-outs between set and restore.</para>
/// </summary>
public sealed class PortalDepthMaskRenderer : IDisposable
{
    private const string VertSrc = @"#version 430 core
layout(location = 0) in vec3 aPos;
uniform mat4 uViewProjection;
uniform int  uPlaneCount;
uniform vec4 uPlanes[8];
uniform int  uForceFarZ;
out float gl_ClipDistance[8];
void main()
{
    vec4 clipPos = uViewProjection * vec4(aPos, 1.0);
    for (int i = 0; i < 8; i++)
        gl_ClipDistance[i] = (i < uPlaneCount) ? dot(uPlanes[i], clipPos) : 1.0;
    if (uForceFarZ == 1)
        clipPos.z = clipPos.w * 0.99999988;   // retail far-z punch constant (0x0059bc90 tail)
    gl_Position = clipPos;
}";

    private const string FragSrc = @"#version 430 core
void main() { }   // depth-only: color writes are masked off by the caller state
";

    private readonly GL _gl;
    private readonly uint _program;
    private readonly uint _vao;
    private readonly uint _vbo;
    private readonly int _locViewProjection;
    private readonly int _locPlaneCount;
    private readonly int _locPlanes;
    private readonly int _locForceFarZ;

    private const int MaxFanVerts = 32;
    private readonly float[] _scratch = new float[MaxFanVerts * 3];

    public PortalDepthMaskRenderer(GL gl)
    {
        _gl = gl ?? throw new ArgumentNullException(nameof(gl));

        uint vs = Compile(ShaderType.VertexShader, VertSrc);
        uint fs = Compile(ShaderType.FragmentShader, FragSrc);
        _program = _gl.CreateProgram();
        _gl.AttachShader(_program, vs);
        _gl.AttachShader(_program, fs);
        _gl.LinkProgram(_program);
        _gl.GetProgram(_program, ProgramPropertyARB.LinkStatus, out int linked);
        if (linked == 0)
            throw new InvalidOperationException($"PortalDepthMask link failed: {_gl.GetProgramInfoLog(_program)}");
        _gl.DeleteShader(vs);
        _gl.DeleteShader(fs);

        _locViewProjection = _gl.GetUniformLocation(_program, "uViewProjection");
        _locPlaneCount = _gl.GetUniformLocation(_program, "uPlaneCount");
        _locPlanes = _gl.GetUniformLocation(_program, "uPlanes");
        _locForceFarZ = _gl.GetUniformLocation(_program, "uForceFarZ");

        _vao = _gl.GenVertexArray();
        _vbo = _gl.GenBuffer();
        _gl.BindVertexArray(_vao);
        _gl.BindBuffer(BufferTargetARB.ArrayBuffer, _vbo);
        unsafe
        {
            _gl.BufferData(BufferTargetARB.ArrayBuffer,
                (nuint)(MaxFanVerts * 3 * sizeof(float)), null, BufferUsageARB.DynamicDraw);
            _gl.VertexAttribPointer(0, 3, VertexAttribPointerType.Float, false, 3 * sizeof(float), (void*)0);
        }
        _gl.EnableVertexAttribArray(0);
        _gl.BindVertexArray(0);
        _gl.BindBuffer(BufferTargetARB.ArrayBuffer, 0);
    }

    private uint Compile(ShaderType type, string src)
    {
        uint s = _gl.CreateShader(type);
        _gl.ShaderSource(s, src);
        _gl.CompileShader(s);
        _gl.GetShader(s, ShaderParameterName.CompileStatus, out int ok);
        if (ok == 0)
            throw new InvalidOperationException($"PortalDepthMask {type} compile failed: {_gl.GetShaderInfoLog(s)}");
        return s;
    }

    /// <summary>
    /// Draw one portal polygon as an invisible depth write, clipped to the
    /// slice's clip-space half-planes. <paramref name="forceFarZ"/> selects
    /// punch (true, retail maxZ1) vs seal (false, retail maxZ2 true depth).
    /// </summary>
    public void DrawDepthFan(
        ReadOnlySpan<Vector3> worldVerts,
        in Matrix4x4 viewProjection,
        ReadOnlySpan<Vector4> planes,
        bool forceFarZ)
    {
        if (worldVerts.Length < 3)
            return;
        int n = Math.Min(worldVerts.Length, MaxFanVerts);
        int planeCount = Math.Min(planes.Length, 8);

        for (int i = 0; i < n; i++)
        {
            _scratch[i * 3 + 0] = worldVerts[i].X;
            _scratch[i * 3 + 1] = worldVerts[i].Y;
            _scratch[i * 3 + 2] = worldVerts[i].Z;
        }

        // ---- set state (everything this draw depends on) ----
        _gl.UseProgram(_program);
        _gl.Disable(EnableCap.Blend);
        _gl.Disable(EnableCap.CullFace);       // portal fans face either way
        _gl.Disable(EnableCap.ScissorTest);
        _gl.Enable(EnableCap.DepthTest);
        _gl.DepthFunc(DepthFunction.Always);   // retail DEPTHTEST ALWAYS
        _gl.DepthMask(true);                   // z-write on
        _gl.ColorMask(false, false, false, false);   // alpha-0 fan ≙ no color
        for (int i = 0; i < planeCount; i++)
            _gl.Enable(EnableCap.ClipDistance0 + i);

        unsafe
        {
            var m = viewProjection;
            _gl.UniformMatrix4(_locViewProjection, 1, false, (float*)&m);
            _gl.Uniform1(_locPlaneCount, planeCount);
            if (planeCount > 0)
            {
                Span<float> p = stackalloc float[planeCount * 4];
                for (int i = 0; i < planeCount; i++)
                {
                    p[i * 4 + 0] = planes[i].X;
                    p[i * 4 + 1] = planes[i].Y;
                    p[i * 4 + 2] = planes[i].Z;
                    p[i * 4 + 3] = planes[i].W;
                }
                fixed (float* pp = p)
                    _gl.Uniform4(_locPlanes, (uint)planeCount, pp);
            }
            _gl.Uniform1(_locForceFarZ, forceFarZ ? 1 : 0);

            _gl.BindVertexArray(_vao);
            _gl.BindBuffer(BufferTargetARB.ArrayBuffer, _vbo);
            fixed (float* v = _scratch)
                _gl.BufferSubData(BufferTargetARB.ArrayBuffer, 0, (nuint)(n * 3 * sizeof(float)), v);
            _gl.DrawArrays(PrimitiveType.TriangleFan, 0, (uint)n);
            _gl.BindVertexArray(0);
            _gl.BindBuffer(BufferTargetARB.ArrayBuffer, 0);
        }

        // ---- restore the frame-global convention ----
        for (int i = 0; i < planeCount; i++)
            _gl.Disable(EnableCap.ClipDistance0 + i);
        _gl.ColorMask(true, true, true, true);
        _gl.DepthFunc(DepthFunction.Less);
        _gl.Enable(EnableCap.CullFace);
        _gl.CullFace(TriangleFace.Back);
        _gl.FrontFace(FrontFaceDirection.CW);
        _gl.UseProgram(0);
    }

    public void Dispose()
    {
        _gl.DeleteProgram(_program);
        _gl.DeleteVertexArray(_vao);
        _gl.DeleteBuffer(_vbo);
    }
}