using System.Numerics;
using AcDream.App.Rendering;
using AcDream.App.Rendering.Gpu;

namespace AcDream.App.Tests.Rendering.Gpu;

/// <summary>
/// One recorded RHI call. Renderer tests assert against the ordered sequence
/// instead of against a live driver, which is what keeps the App suite runnable
/// on a machine with no GPU while renderers migrate onto <see cref="IGpuDevice"/>
/// during Campaign V.
/// </summary>
internal abstract record GpuRecordedCall;

internal sealed record GpuRecordedFrameBegin(long Serial, int SlotIndex) : GpuRecordedCall;

internal sealed record GpuRecordedFrameEnd(long Serial) : GpuRecordedCall;

internal sealed record GpuRecordedRingAllocation(GpuRingUsage Usage, int ByteCount, uint OffsetBytes) : GpuRecordedCall;

internal sealed record GpuRecordedPassBegin(string Name, int SampleCount) : GpuRecordedCall;

internal sealed record GpuRecordedPassEnd(string Name) : GpuRecordedCall;

internal sealed record GpuRecordedPipelineBind(string PipelineName) : GpuRecordedCall;

internal sealed record GpuRecordedStorageBind(uint Binding, string BufferName, uint OffsetBytes, uint SizeBytes)
    : GpuRecordedCall;

internal sealed record GpuRecordedUniformBind(uint Binding, string BufferName, uint OffsetBytes, uint SizeBytes)
    : GpuRecordedCall;

internal sealed record GpuRecordedVertexBind(uint Binding, string BufferName, uint OffsetBytes) : GpuRecordedCall;
internal sealed record GpuRecordedStencil(GpuStencilState Stencil) : GpuRecordedCall;

internal sealed record GpuRecordedIndexBind(string BufferName, uint OffsetBytes, GpuIndexType IndexType)
    : GpuRecordedCall;

internal sealed record GpuRecordedPushConstants(GpuPushConstants Constants) : GpuRecordedCall;

internal sealed record GpuRecordedViewport(int X, int Y, int Width, int Height) : GpuRecordedCall;

internal sealed record GpuRecordedScissor(int X, int Y, int Width, int Height) : GpuRecordedCall;

internal sealed record GpuRecordedCullMode(GpuCullMode CullMode) : GpuRecordedCall;

internal sealed record GpuRecordedFrontFace(GpuFrontFace FrontFace) : GpuRecordedCall;

internal sealed record GpuRecordedDepthWrite(bool Enabled) : GpuRecordedCall;

internal sealed record GpuRecordedDrawIndexed(
    uint IndexCount,
    uint InstanceCount,
    uint FirstIndex,
    int VertexOffset,
    uint FirstInstance) : GpuRecordedCall;

internal sealed record GpuRecordedDraw(
    uint VertexCount,
    uint InstanceCount,
    uint FirstVertex,
    uint FirstInstance) : GpuRecordedCall;

internal sealed record GpuRecordedMultiDrawIndirect(
    string BufferName,
    uint OffsetBytes,
    uint DrawCount,
    uint StrideBytes) : GpuRecordedCall;

internal sealed record GpuRecordedTextureRegistration(string TextureName, GpuSamplerDescription Sampler, uint Slot)
    : GpuRecordedCall;

internal sealed record GpuRecordedTextureRelease(uint Slot) : GpuRecordedCall;

/// <summary>
/// In-memory <see cref="IGpuDevice"/> that owns no driver objects. Ring
/// allocations are backed by a real byte array, so a test can drive a renderer
/// and then read back exactly what it wrote — the same bytes a driver would have
/// seen. Everything else is recorded into <see cref="Calls"/> in submission order.
/// </summary>
internal sealed class RecordingGpuDevice : IGpuDevice
{
    private const int DefaultRingCapacityBytes = 8 * 1024 * 1024;

    private readonly List<GpuRecordedCall> _calls = [];
    private readonly List<Action> _queuedActions = [];
    private readonly Dictionary<GpuSamplerDescription, RecordingGpuSampler> _samplers = [];
    private readonly byte[] _ring;
    private readonly Stack<uint> _freeTextureSlots = new();

    private uint _nextTextureSlot;
    private uint _ringCursor;
    private long _serial;
    private RecordingGpuFrame? _openFrame;
    private bool _disposed;

    public RecordingGpuDevice(int ringCapacityBytes = DefaultRingCapacityBytes)
    {
        ArgumentOutOfRangeException.ThrowIfLessThan(ringCapacityBytes, 1);
        _ring = new byte[ringCapacityBytes];
        RingBuffer = new RecordingGpuBuffer(new GpuBufferDescription(
            "test-ring",
            ringCapacityBytes,
            GpuBufferUsage.Storage | GpuBufferUsage.Uniform | GpuBufferUsage.Indirect,
            GpuMemoryResidency.HostWritable));

        RecordingGpuTexture placeholder = new("default-white", GpuTextureKind.Texture2D, GpuTextureFormat.Rgba8Unorm, 1, 1, 1, 1);
        DefaultTextureSlot = RegisterTexture(placeholder, CreateSampler(GpuSamplerDescription.UiNearest));
    }

    /// <summary>Every recorded call, in submission order.</summary>
    public IReadOnlyList<GpuRecordedCall> Calls => _calls;

    /// <summary>Backing store for ring allocations, so tests can read what a renderer wrote.</summary>
    public ReadOnlySpan<byte> RingBytes => _ring;

    /// <summary>Number of ring bytes handed out during the currently open (or most recent) frame.</summary>
    public uint RingBytesAllocated => _ringCursor;

    public int OpenFrameCount { get; private set; }

    public int LiveTextureSlotCount => (int)_nextTextureSlot - _freeTextureSlots.Count;

    public GpuBackendKind Backend => GpuBackendKind.Recording;

    public GpuCapabilityRecord Capabilities { get; init; } = new()
    {
        Backend = GpuBackendKind.Recording,
        DeviceName = "recording",
        DriverInfo = "in-memory test double",
        ApiVersion = "n/a",
        MaxTextureTableSlots = GpuBindingModel.TextureTableCapacity,
        MaxStorageBufferBindings = GpuBindingModel.StorageBindingCount,
        MaxPushConstantBytes = GpuBindingModel.MaxPushConstantBytes,
        MinStorageBufferOffsetAlignment = 256,
        MinUniformBufferOffsetAlignment = 256,
        MaxClipDistances = GpuBindingModel.ClipPlanesPerSlot,
        MaxSampleCount = 8,
        SupportsMultiDrawIndirect = true,
        SupportsDrawParameters = true,
        SupportsTextureCompressionBc = true,
        SupportsTimestampQueries = true,
        SupportsPersistentlyMappedRings = true,
    };

    public IGpuResourceRetirementQueue Retirement => ImmediateGpuResourceRetirementQueue.Instance;

    public IGpuTimerPool Timers { get; } = new RecordingGpuTimerPool();

    public GpuTextureSlot DefaultTextureSlot { get; }

    public void Clear() => _calls.Clear();

    public IGpuBuffer CreateBuffer(in GpuBufferDescription description) =>
        new RecordingGpuBuffer(description);

    /// <summary>
    /// Campaign V slice V6i-2: every image this device made, in creation order.
    /// A caller that creates its own textures internally — the world texture
    /// arrays and the terrain atlas do — has no other way to assert what landed
    /// on them.
    /// </summary>
    public IReadOnlyList<RecordingGpuTexture> CreatedTextures => _createdTextures;

    private readonly List<RecordingGpuTexture> _createdTextures = [];

    public IGpuTexture CreateTexture(in GpuTextureDescription description)
    {
        RecordingGpuTexture texture = new(
            description.Name,
            description.Kind,
            description.Format,
            description.Width,
            description.Height,
            description.LayerCount,
            description.MipLevelCount);
        _createdTextures.Add(texture);
        return texture;
    }

    public IGpuSampler CreateSampler(in GpuSamplerDescription description)
    {
        if (_samplers.TryGetValue(description, out RecordingGpuSampler? existing))
            return existing;

        RecordingGpuSampler created = new(description);
        _samplers.Add(description, created);
        return created;
    }

    public IGpuPipeline CreatePipeline(GpuPipelineDescription description)
    {
        ArgumentNullException.ThrowIfNull(description);
        return new RecordingGpuPipeline(description);
    }

    public IGpuRenderTarget CreateRenderTarget(in GpuRenderTargetDescription description) =>
        new RecordingGpuRenderTarget(description);

    public GpuTextureSlot RegisterTexture(IGpuTexture texture, IGpuSampler sampler)
    {
        ArgumentNullException.ThrowIfNull(texture);
        ArgumentNullException.ThrowIfNull(sampler);

        uint slot = _freeTextureSlots.Count > 0 ? _freeTextureSlots.Pop() : _nextTextureSlot++;
        _calls.Add(new GpuRecordedTextureRegistration(texture.Name, sampler.Description, slot));
        return new GpuTextureSlot(slot);
    }

    public void ReleaseTextureSlot(GpuTextureSlot slot)
    {
        if (!slot.IsAssigned)
            throw new ArgumentException("Cannot release an unassigned texture slot.", nameof(slot));

        _freeTextureSlots.Push(slot.Index);
        _calls.Add(new GpuRecordedTextureRelease(slot.Index));
    }

    public IGpuFrame BeginFrame()
    {
        ObjectDisposedException.ThrowIf(_disposed, this);
        if (_openFrame is not null)
            throw new InvalidOperationException("The previous frame must end before another begins.");

        _ringCursor = 0;
        long serial = ++_serial;
        int slotIndex = (int)((serial - 1) % 2);
        _calls.Add(new GpuRecordedFrameBegin(serial, slotIndex));
        OpenFrameCount++;
        _openFrame = new RecordingGpuFrame(this, serial, slotIndex);
        return _openFrame;
    }

    public void QueueDeviceAction(Action action)
    {
        ArgumentNullException.ThrowIfNull(action);
        _queuedActions.Add(action);
    }

    public void ProcessDeviceActions()
    {
        Action[] pending = [.. _queuedActions];
        _queuedActions.Clear();
        foreach (Action action in pending)
            action();
    }

    public byte[] CaptureBackbuffer(int width, int height)
    {
        ArgumentOutOfRangeException.ThrowIfNegativeOrZero(width);
        ArgumentOutOfRangeException.ThrowIfNegativeOrZero(height);
        return new byte[checked(width * height * 4)];
    }

    public void WaitIdle() => ProcessDeviceActions();

    public void Dispose() => _disposed = true;

    internal void Record(GpuRecordedCall call) => _calls.Add(call);

    internal GpuRingAllocation Allocate(int byteCount, GpuRingUsage usage)
    {
        ArgumentOutOfRangeException.ThrowIfNegative(byteCount);

        uint alignment = usage switch
        {
            GpuRingUsage.Storage => Capabilities.MinStorageBufferOffsetAlignment,
            GpuRingUsage.Uniform => Capabilities.MinUniformBufferOffsetAlignment,
            _ => 4u,
        };

        uint aligned = AlignUp(_ringCursor, alignment);
        if (aligned + (uint)byteCount > (uint)_ring.Length)
        {
            throw new InvalidOperationException(
                $"Ring allocation of {byteCount} bytes for {usage} exceeds the {_ring.Length}-byte test ring.");
        }

        _ringCursor = aligned + (uint)byteCount;
        _calls.Add(new GpuRecordedRingAllocation(usage, byteCount, aligned));
        return new GpuRingAllocation(RingBuffer, aligned, _ring.AsSpan((int)aligned, byteCount));
    }

    internal IGpuBuffer RingBuffer { get; }

    internal void CloseFrame(RecordingGpuFrame frame)
    {
        if (!ReferenceEquals(_openFrame, frame))
            return;

        _calls.Add(new GpuRecordedFrameEnd(frame.Serial));
        OpenFrameCount--;
        _openFrame = null;
    }

    private static uint AlignUp(uint value, uint alignment) =>
        alignment <= 1 ? value : (value + alignment - 1) / alignment * alignment;
}

internal sealed class RecordingGpuFrame(RecordingGpuDevice device, long serial, int slotIndex) : IGpuFrame
{
    private bool _ended;

    public int SlotIndex { get; } = slotIndex;

    public long Serial { get; } = serial;

    public GpuRingAllocation AllocateRing(int byteCount, GpuRingUsage usage) => device.Allocate(byteCount, usage);

    public IGpuPassEncoder BeginPass(GpuPassDescription description)
    {
        ArgumentNullException.ThrowIfNull(description);
        device.Record(new GpuRecordedPassBegin(description.Name, description.SampleCount));
        return new RecordingGpuPassEncoder(device, description);
    }

    public void End()
    {
        if (_ended)
            return;

        _ended = true;
        device.CloseFrame(this);
    }

    public void Dispose() => End();
}

internal sealed class RecordingGpuPassEncoder(RecordingGpuDevice device, GpuPassDescription pass) : IGpuPassEncoder
{
    private bool _closed;

    public GpuPassDescription Pass { get; } = pass;

    public void BindPipeline(IGpuPipeline pipeline)
    {
        ArgumentNullException.ThrowIfNull(pipeline);
        device.Record(new GpuRecordedPipelineBind(pipeline.Description.Name));
    }

    public void BindStorageBuffer(uint binding, IGpuBuffer buffer, uint offsetBytes, uint sizeBytes)
    {
        ArgumentNullException.ThrowIfNull(buffer);
        device.Record(new GpuRecordedStorageBind(binding, buffer.Name, offsetBytes, sizeBytes));
    }

    public void BindUniformBuffer(uint binding, IGpuBuffer buffer, uint offsetBytes, uint sizeBytes)
    {
        ArgumentNullException.ThrowIfNull(buffer);
        device.Record(new GpuRecordedUniformBind(binding, buffer.Name, offsetBytes, sizeBytes));
    }

    public void BindVertexBuffer(uint binding, IGpuBuffer buffer, uint offsetBytes)
    {
        ArgumentNullException.ThrowIfNull(buffer);
        device.Record(new GpuRecordedVertexBind(binding, buffer.Name, offsetBytes));
    }

    public void BindIndexBuffer(IGpuBuffer buffer, uint offsetBytes, GpuIndexType indexType)
    {
        ArgumentNullException.ThrowIfNull(buffer);
        device.Record(new GpuRecordedIndexBind(buffer.Name, offsetBytes, indexType));
    }

    public void SetPushConstants(in GpuPushConstants constants) =>
        device.Record(new GpuRecordedPushConstants(constants));

    public void SetViewport(int x, int y, int width, int height) =>
        device.Record(new GpuRecordedViewport(x, y, width, height));

    public void SetScissor(int x, int y, int width, int height) =>
        device.Record(new GpuRecordedScissor(x, y, width, height));

    public void SetCullMode(GpuCullMode cullMode) => device.Record(new GpuRecordedCullMode(cullMode));

    public void SetFrontFace(GpuFrontFace frontFace) => device.Record(new GpuRecordedFrontFace(frontFace));

    public void SetStencil(in GpuStencilState stencil) => device.Record(new GpuRecordedStencil(stencil));

    public void SetDepthWrite(bool enabled) => device.Record(new GpuRecordedDepthWrite(enabled));

    public void DrawIndexed(uint indexCount, uint instanceCount, uint firstIndex, int vertexOffset, uint firstInstance) =>
        device.Record(new GpuRecordedDrawIndexed(indexCount, instanceCount, firstIndex, vertexOffset, firstInstance));

    public void Draw(uint vertexCount, uint instanceCount, uint firstVertex, uint firstInstance) =>
        device.Record(new GpuRecordedDraw(vertexCount, instanceCount, firstVertex, firstInstance));

    public void MultiDrawIndexedIndirect(IGpuBuffer commands, uint offsetBytes, uint drawCount, uint strideBytes)
    {
        ArgumentNullException.ThrowIfNull(commands);
        device.Record(new GpuRecordedMultiDrawIndirect(commands.Name, offsetBytes, drawCount, strideBytes));
    }

    public IDisposable BeginTimerScope(string scopeName) => NullDisposable.Instance;

    public void Dispose()
    {
        if (_closed)
            return;

        _closed = true;
        device.Record(new GpuRecordedPassEnd(Pass.Name));
    }

    private sealed class NullDisposable : IDisposable
    {
        public static NullDisposable Instance { get; } = new();

        public void Dispose()
        {
        }
    }
}

internal sealed class RecordingGpuBuffer(GpuBufferDescription description) : IGpuBuffer
{
    private readonly byte[] _storage = new byte[description.SizeBytes];

    public string Name { get; } = description.Name;

    public long SizeBytes { get; } = description.SizeBytes;

    public GpuBufferUsage Usage { get; } = description.Usage;

    public GpuMemoryResidency Residency { get; } = description.Residency;

    public bool IsDisposed { get; private set; }

    public void Upload(long offsetBytes, ReadOnlySpan<byte> data) =>
        data.CopyTo(_storage.AsSpan((int)offsetBytes, data.Length));

    public void CopyTo(IGpuBuffer destination, long sourceOffsetBytes, long destinationOffsetBytes, long byteCount)
    {
        ArgumentNullException.ThrowIfNull(destination);
        if (destination is not RecordingGpuBuffer target)
            throw new ArgumentException("Recording buffers can only copy to recording buffers.", nameof(destination));

        _storage.AsSpan((int)sourceOffsetBytes, (int)byteCount)
            .CopyTo(target._storage.AsSpan((int)destinationOffsetBytes, (int)byteCount));
    }

    public void Read(long offsetBytes, Span<byte> destination) =>
        _storage.AsSpan((int)offsetBytes, destination.Length).CopyTo(destination);

    public void Dispose() => IsDisposed = true;
}

internal sealed class RecordingGpuTexture(
    string name,
    GpuTextureKind kind,
    GpuTextureFormat format,
    int width,
    int height,
    int layerCount,
    int mipLevelCount) : IGpuTexture
{
    private readonly List<(int MipLevel, int Layer, int ByteCount)> _uploads = [];

    public string Name { get; } = name;

    public GpuTextureKind Kind { get; } = kind;

    public GpuTextureFormat Format { get; } = format;

    public int Width { get; } = width;

    public int Height { get; } = height;

    public int LayerCount { get; } = layerCount;

    public int MipLevelCount { get; } = mipLevelCount;

    public bool MipChainGenerated { get; private set; }

    public bool IsDisposed { get; private set; }

    public IReadOnlyList<(int MipLevel, int Layer, int ByteCount)> Uploads => _uploads;

    public void Upload(int mipLevel, int layer, ReadOnlySpan<byte> data) =>
        _uploads.Add((mipLevel, layer, data.Length));

    public void GenerateMipChain() => MipChainGenerated = true;

    public void Dispose() => IsDisposed = true;
}

internal sealed class RecordingGpuSampler(GpuSamplerDescription description) : IGpuSampler
{
    public GpuSamplerDescription Description { get; } = description;

    public bool IsDisposed { get; private set; }

    public void Dispose() => IsDisposed = true;
}

internal sealed class RecordingGpuPipeline(GpuPipelineDescription description) : IGpuPipeline
{
    public GpuPipelineDescription Description { get; } = description;

    public bool IsDisposed { get; private set; }

    public void Dispose() => IsDisposed = true;
}

internal sealed class RecordingGpuRenderTarget : IGpuRenderTarget
{
    public RecordingGpuRenderTarget(GpuRenderTargetDescription description)
    {
        Description = description;
        ColorTexture = new RecordingGpuTexture(
            $"{description.Name}-color",
            GpuTextureKind.Texture2D,
            description.ColorFormat,
            description.Width,
            description.Height,
            layerCount: 1,
            mipLevelCount: 1);
    }

    public GpuRenderTargetDescription Description { get; }

    public IGpuTexture ColorTexture { get; }

    public bool IsDisposed { get; private set; }

    public void Dispose() => IsDisposed = true;
}

internal sealed class RecordingGpuTimerPool : IGpuTimerPool
{
    public bool IsSupported => false;

    public bool TryResolve(string scopeName, out double milliseconds)
    {
        milliseconds = 0d;
        return false;
    }
}

/// <summary>Convenience helpers so renderer tests read as assertions, not as list surgery.</summary>
internal static class RecordingGpuDeviceAssertions
{
    public static IEnumerable<T> OfKind<T>(this RecordingGpuDevice device) where T : GpuRecordedCall =>
        device.Calls.OfType<T>();

    public static Vector4 ClearColorOf(this GpuPassDescription pass) => pass.Color.ClearColor;
}