acdream/src/AcDream.App/Rendering/Gpu/Gl/GlGpuPassEncoder.cs

using AcDream.App.Rendering.Wb;
using Silk.NET.OpenGL;

namespace AcDream.App.Rendering.Gpu.Gl;

/// <summary>
/// Records one pass's draw work. Binding calls translate almost mechanically
/// to GL (a storage/uniform binding is <c>glBindBufferRange</c>, an indexed
/// draw is <c>glDrawElementsInstancedBaseVertexBaseInstance</c>, and so on);
/// the two pieces of real logic are the render-state diff applied on
/// <see cref="BindPipeline"/> / the dynamic setters, and the "flush dirty
/// ring + texture-table bytes immediately before every draw" discipline
/// described on <see cref="GlGpuDevice"/>.
/// </summary>
internal sealed class GlGpuPassEncoder : IGpuPassEncoder
{
    private readonly GlGpuDevice _device;
    private readonly GlGpuFrame _frame;
    private readonly GL _gl;
    private readonly IGlAmbientStateApi _ambientApi;
    private readonly GlAmbientCapabilityState _ambientOnEntry;
    private bool _closed;

    private GlGpuPipeline? _currentPipeline;
    private GpuIndexType _currentIndexType = GpuIndexType.UInt16;
    private uint _currentIndexBufferBaseOffset;
    private GpuPushConstants? _currentPushConstants;

    internal GlGpuPassEncoder(GlGpuDevice device, GlGpuFrame frame, GpuPassDescription pass)
    {
        _device = device;
        _frame = frame;
        _gl = device.Gl;
        Pass = pass;

        // Campaign V slice V4a (2026-07-27 revert postmortem, plan §7.1 rule 1):
        // capture every ambient capability a bound pipeline can change, so
        // Dispose can put it back. Every acdream renderer is still raw GL
        // until V4c/V4d, so each one assumes whatever capability state the
        // PREVIOUS renderer left behind is still there — GL_MULTISAMPLE and
        // GL_SAMPLE_ALPHA_TO_COVERAGE in particular are set once per frame by
        // quality settings and never re-asserted per draw. The first V4a
        // attempt bound a pipeline that changed this state and never restored
        // it, so the world drew without multisampling from the first UI frame
        // on. Capturing here and restoring on Dispose keeps the GL backend's
        // behaviour-preserving property true at this seam. Deleted at V4h
        // once nothing raw-GL remains.
        _ambientApi = new SilkGlAmbientStateApi(_gl);
        _ambientOnEntry = GlAmbientCapabilityState.Capture(_ambientApi);

        // Campaign V slice V6d. GL_MULTISAMPLE is the one piece of pass state
        // with no representation in GpuPipelineDescription, and the pass's own
        // SampleCount is the contract's answer for it: a single-sampled pass
        // does not multisample. Until now the retained UI asserted that with a
        // raw glDisable of its own — exactly the kind of state a
        // backend-neutral renderer cannot own. Quality settings enable
        // GL_MULTISAMPLE once per frame for the world, and if it leaks into the
        // UI pass every glyph's soft alpha edge becomes dithered coverage
        // instead of a clean alpha blend (the "fuzzy text" artifact). The
        // ambient capture above puts it back on Dispose, so the raw-GL world
        // renderers that follow are unaffected.
        _ambientApi.SetCapability(EnableCap.Multisample, pass.SampleCount > 1);
    }

    public GpuPassDescription Pass { get; }

    public void BindPipeline(IGpuPipeline pipeline)
    {
        ArgumentNullException.ThrowIfNull(pipeline);
        ThrowIfClosed();
        var p = (GlGpuPipeline)pipeline;
        _currentPipeline = p;

        GpuPipelineDescription description = p.Description;
        var desired = new GlRenderStateSnapshot(
            p.GlProgram,
            description.Blend,
            description.Depth.Test,
            description.Depth.Write,
            description.Depth.Compare,
            description.Cull,
            description.FrontFace,
            description.AlphaToCoverage,
            description.ColorWrite,
            description.StencilTest,
            description.Stencil);
        _device.ApplyRenderState(desired);

        _gl.BindVertexArray(p.GlVertexArray);
        GLHelpers.ThrowOnResourceError(_gl, $"bind pipeline '{description.Name}' VAO");

        // Campaign V slice V6d: the device's texture table is bound with the
        // pipeline, the GL analogue of the Vulkan backend binding descriptor
        // set 2 on every draw. It has to happen here rather than once per frame
        // because every raw-GL world renderer binds its OWN private handle
        // table at this same binding before its own draws, with its own slot
        // numbering; an RHI shader that read that instead would sample a
        // plausible but entirely unrelated texture. Removed at V4h with the
        // per-renderer tables.
        _gl.BindBufferBase(
            GLEnum.ShaderStorageBuffer,
            GpuBindingModel.StorageTextureTable,
            _device.TextureTableGlName);
        GLHelpers.ThrowOnResourceError(_gl, $"bind pipeline '{description.Name}' texture table");

        // Push constants "survive pipeline changes within a pass" per the
        // IGpuPassEncoder contract. GL uniforms are per-program state, so the
        // GL backend must explicitly re-apply the last value to the newly
        // bound program to honour that — Vulkan gets this for free from a
        // shared pipeline layout.
        if (_currentPushConstants is { } constants)
            _device.PushConstants.Apply(p.GlProgram, in constants);
    }

    public void BindStorageBuffer(uint binding, IGpuBuffer buffer, uint offsetBytes, uint sizeBytes)
    {
        ThrowIfClosed();
        var b = RequireGlBuffer(buffer);
        _gl.BindBufferRange(GLEnum.ShaderStorageBuffer, binding, b.GlName, (nint)offsetBytes, sizeBytes);
        GLHelpers.ThrowOnResourceError(_gl, $"bind storage buffer '{buffer.Name}' at binding {binding}");
    }

    public void BindUniformBuffer(uint binding, IGpuBuffer buffer, uint offsetBytes, uint sizeBytes)
    {
        ThrowIfClosed();
        var b = RequireGlBuffer(buffer);
        _gl.BindBufferRange(GLEnum.UniformBuffer, binding, b.GlName, (nint)offsetBytes, sizeBytes);
        GLHelpers.ThrowOnResourceError(_gl, $"bind uniform buffer '{buffer.Name}' at binding {binding}");
    }

    public unsafe void BindVertexBuffer(uint binding, IGpuBuffer buffer, uint offsetBytes)
    {
        ThrowIfClosed();
        if (_currentPipeline is not { } pipeline)
            throw new InvalidOperationException("BindPipeline must be called before BindVertexBuffer.");
        var b = RequireGlBuffer(buffer);

        _gl.BindBuffer(GLEnum.ArrayBuffer, b.GlName);
        GpuVertexLayout layout = pipeline.Description.VertexLayout;
        // Slice V6l: only the attributes this binding actually supplies. GL has
        // no binding indirection of its own — glVertexAttribPointer records the
        // currently bound ARRAY_BUFFER per attribute — so the binding index is
        // resolved here, by filtering, rather than by the driver.
        uint stride = layout.StrideOf(binding);
        foreach (GpuVertexAttribute attribute in layout.Attributes)
        {
            if (attribute.Binding != binding)
                continue;

            GlVertexAttributeShape shape = GlEnumMapping.VertexShapeOf(attribute.Format);
            nint attributeOffset = (nint)(offsetBytes + attribute.OffsetBytes);
            if (shape.Integer)
            {
                // An integer shader input (uvec4) must come through the I-form.
                // Supplying it via glVertexAttribPointer leaves the value undefined.
                _gl.VertexAttribIPointer(
                    attribute.Location,
                    shape.ComponentCount,
                    (VertexAttribIType)shape.Type,
                    stride,
                    (void*)attributeOffset);
            }
            else
            {
                _gl.VertexAttribPointer(
                    attribute.Location,
                    shape.ComponentCount,
                    shape.Type,
                    shape.Normalized,
                    stride,
                    (void*)attributeOffset);
            }
        }
        GLHelpers.ThrowOnResourceError(_gl, $"bind vertex buffer '{buffer.Name}'");
        _gl.BindBuffer(GLEnum.ArrayBuffer, 0);
    }

    public void BindIndexBuffer(IGpuBuffer buffer, uint offsetBytes, GpuIndexType indexType)
    {
        ThrowIfClosed();
        var b = RequireGlBuffer(buffer);
        _currentIndexType = indexType;
        _currentIndexBufferBaseOffset = offsetBytes;
        _gl.BindBuffer(GLEnum.ElementArrayBuffer, b.GlName);
        GLHelpers.ThrowOnResourceError(_gl, $"bind index buffer '{buffer.Name}'");
    }

    public void SetPushConstants(in GpuPushConstants constants)
    {
        ThrowIfClosed();
        _currentPushConstants = constants;
        if (_currentPipeline is { } pipeline)
            _device.PushConstants.Apply(pipeline.GlProgram, in constants);
    }

    public void SetViewport(int x, int y, int width, int height)
    {
        ThrowIfClosed();
        _gl.Viewport(x, y, (uint)width, (uint)height);
    }

    public void SetScissor(int x, int y, int width, int height)
    {
        ThrowIfClosed();
        _gl.Enable(EnableCap.ScissorTest);
        _gl.Scissor(x, y, (uint)width, (uint)height);
    }

    public void SetCullMode(GpuCullMode cullMode)
    {
        ThrowIfClosed();
        _device.ApplyRenderState(_device.CurrentRenderState with { Cull = cullMode });
    }

    public void SetFrontFace(GpuFrontFace frontFace)
    {
        ThrowIfClosed();
        _device.ApplyRenderState(_device.CurrentRenderState with { FrontFace = frontFace });
    }

    public void SetDepthWrite(bool enabled)
    {
        ThrowIfClosed();
        _device.ApplyRenderState(_device.CurrentRenderState with { DepthWrite = enabled });
    }

    public void SetStencil(in GpuStencilState stencil)
    {
        ThrowIfClosed();
        _device.ApplyRenderState(_device.CurrentRenderState with { Stencil = stencil });
    }

    public unsafe void DrawIndexed(uint indexCount, uint instanceCount, uint firstIndex, int vertexOffset, uint firstInstance)
    {
        ThrowIfClosed();
        _device.FlushBeforeDraw(_frame.SlotIndex);
        int indexSize = GlEnumMapping.IndexSizeBytesOf(_currentIndexType);
        nint indexOffset = (nint)(_currentIndexBufferBaseOffset + firstIndex * (uint)indexSize);
        _gl.DrawElementsInstancedBaseVertexBaseInstance(
            GlEnumMapping.PrimitiveTypeOf(RequirePipeline().Description.Topology),
            indexCount,
            GlEnumMapping.DrawElementsTypeOf(_currentIndexType),
            (void*)indexOffset,
            instanceCount,
            vertexOffset,
            firstInstance);
        GLHelpers.ThrowOnResourceError(_gl, "DrawIndexed");
    }

    public void Draw(uint vertexCount, uint instanceCount, uint firstVertex, uint firstInstance)
    {
        ThrowIfClosed();
        _device.FlushBeforeDraw(_frame.SlotIndex);
        _gl.DrawArraysInstancedBaseInstance(
            (GLEnum)GlEnumMapping.PrimitiveTypeOf(RequirePipeline().Description.Topology),
            (int)firstVertex,
            vertexCount,
            instanceCount,
            firstInstance);
        GLHelpers.ThrowOnResourceError(_gl, "Draw");
    }

    public unsafe void MultiDrawIndexedIndirect(IGpuBuffer commands, uint offsetBytes, uint drawCount, uint strideBytes)
    {
        ThrowIfClosed();
        var indirect = RequireGlBuffer(commands);
        _device.FlushBeforeDraw(_frame.SlotIndex);
        _gl.BindBuffer(GLEnum.DrawIndirectBuffer, indirect.GlName);
        _gl.MultiDrawElementsIndirect(
            GlEnumMapping.PrimitiveTypeOf(RequirePipeline().Description.Topology),
            GlEnumMapping.DrawElementsTypeOf(_currentIndexType),
            (void*)(nint)offsetBytes,
            drawCount,
            strideBytes);
        GLHelpers.ThrowOnResourceError(_gl, "MultiDrawIndexedIndirect");
        _gl.BindBuffer(GLEnum.DrawIndirectBuffer, 0);
    }

    public IDisposable BeginTimerScope(string scopeName) => _device.TimerPool.BeginScope(scopeName);

    public void Dispose()
    {
        if (_closed)
            return;
        _closed = true;
        // GL has no store-op work to do here: GpuStoreOp.Resolve was already
        // rejected at BeginPass (V1 targets are single-sampled), and
        // Store/DontCare need no explicit action — the framebuffer's contents
        // simply persist until the next pass rebinds a target.
        //
        // Restore whatever capability state was ambient before this pass
        // opened (see the constructor's comment) so a still-raw-GL renderer
        // running immediately after this pass sees exactly what it would have
        // seen had this pass never bound a pipeline.
        _ambientOnEntry.Restore(_ambientApi);
        _frame.ClosePass(this);
    }

    private GlGpuPipeline RequirePipeline() =>
        _currentPipeline ?? throw new InvalidOperationException("BindPipeline must be called before drawing.");

    private static GlGpuBuffer RequireGlBuffer(IGpuBuffer buffer)
    {
        ArgumentNullException.ThrowIfNull(buffer);
        if (buffer is not GlGpuBuffer glBuffer)
            throw new ArgumentException("The GL backend can only bind GL buffers.", nameof(buffer));
        return glBuffer;
    }

    private void ThrowIfClosed()
    {
        if (_closed)
            throw new ObjectDisposedException(nameof(GlGpuPassEncoder));
    }
}