using System.Numerics;
using AcDream.App.Rendering.Wb;
using AcDream.Core.Terrain;
using Silk.NET.OpenGL;

namespace AcDream.App.Rendering;

/// <summary>
/// Phase N.5b modern terrain dispatcher. Single global VBO/EBO with a slot
/// allocator (one slot per landblock, 384 verts × 40 bytes = 15,360 bytes
/// per slot). Per-frame: build a DrawElementsIndirectCommand array from
/// visible slots, upload, dispatch via glMultiDrawElementsIndirect. Atlas
/// textures bound via bindless handles set per-frame as sampler uniforms.
///
/// Total ~6-8 GL calls per frame for terrain regardless of visible
/// landblock count.
/// </summary>
public sealed unsafe class TerrainModernRenderer : IDisposable
{
    // VertsPerLandblock MUST stay divisible by 6 — terrain_modern.vert uses
    // `gl_VertexID % 6` to pick the cell-corner index (BL/BR/TR/TL), and
    // because we bake `slot * VertsPerLandblock` into indices CPU-side and
    // pass BaseVertex=0 to MultiDrawElementsIndirect, gl_VertexID becomes
    // `slot * VertsPerLandblock + local_index`. The shader's modulo-6 only
    // reduces to `local_index % 6` because 384 is a multiple of 6. Changing
    // either constant without auditing the shader will silently mis-render.
    private const int VertsPerLandblock = LandblockMesh.VerticesPerLandblock;  // 384 (= 64 cells * 6 verts)
    private const int IndicesPerLandblock = VertsPerLandblock;
    private const int VertexSize = 40;  // sizeof(TerrainVertex)
    private const int IndexSize = sizeof(uint);
    private const float LandblockSize = LandblockMesh.LandblockSize;  // 192

    private readonly GL _gl;
    private readonly BindlessSupport _bindless;
    private readonly Shader _shader;
    private readonly TerrainAtlas _atlas;

    /// <summary>A.5 T22.5: exposes the terrain atlas so callers can update
    /// anisotropic level mid-session via <see cref="TerrainAtlas.SetAnisotropic"/>.</summary>
    public TerrainAtlas Atlas => _atlas;

    private readonly TerrainSlotAllocator _alloc;

    // Per-slot live data (index by slot integer; null entries are unused slots).
    private SlotData?[] _slots;

    // Reverse map: landblockId -> slot, for RemoveLandblock and replacement.
    private readonly Dictionary<uint, int> _idToSlot = new();

    // GPU buffers.
    private uint _globalVao;
    private uint _globalVbo;
    private uint _globalEbo;
    private uint _indirectBuffer;
    private int  _indirectCapacity;

    // Cached uvec2-handle uniform locations (matrix uniforms are set by name via Shader.SetMatrix4).
    private int _uTerrainHandleLoc;
    private int _uAlphaHandleLoc;

    // Reusable per-frame buffers.
    private readonly List<int> _visibleSlots = new();
    private DrawElementsIndirectCommand[] _deicScratch = Array.Empty<DrawElementsIndirectCommand>();

    // Diag.
    public int LoadedSlots   => _alloc.LoadedCount;
    public int VisibleSlots  => _visibleSlots.Count;
    public int CapacitySlots => _alloc.Capacity;

    public TerrainModernRenderer(
        GL gl,
        BindlessSupport bindless,
        Shader shader,
        TerrainAtlas atlas,
        int initialSlotCapacity = 64)
    {
        _gl = gl;
        _bindless = bindless;
        _shader = shader;
        _atlas = atlas;
        _alloc = new TerrainSlotAllocator(initialSlotCapacity);
        _slots = new SlotData?[initialSlotCapacity];

        _uTerrainHandleLoc = _gl.GetUniformLocation(_shader.Program, "uTerrainHandle");
        _uAlphaHandleLoc   = _gl.GetUniformLocation(_shader.Program, "uAlphaHandle");

        _globalVao = _gl.GenVertexArray();
        _globalVbo = _gl.GenBuffer();
        _globalEbo = _gl.GenBuffer();
        AllocateGpuBuffers(initialSlotCapacity);
        ConfigureVao();

        _indirectBuffer = _gl.GenBuffer();
    }

    /// <summary>
    /// Two-tier streaming entry point. Accepts a prebuilt mesh from
    /// <see cref="LandblockStreamResult.Loaded.MeshData"/> built on the worker
    /// thread, together with the world-space origin computed by the caller
    /// (render-thread GameWindow derives it from landblockId + liveCenterX/Y).
    ///
    /// Delegates to <see cref="AddLandblock(uint,LandblockMeshData,Vector3)"/>
    /// so both paths share one upload path. Per Phase A.5 spec T15.
    /// </summary>
    public void AddLandblockWithMesh(uint landblockId, LandblockMeshData meshData, Vector3 worldOrigin)
        => AddLandblock(landblockId, meshData, worldOrigin);

    public void AddLandblock(uint landblockId, LandblockMeshData meshData, Vector3 worldOrigin)
    {
        ArgumentNullException.ThrowIfNull(meshData);
        if (meshData.Vertices.Length != VertsPerLandblock)
            throw new ArgumentException(
                $"Expected {VertsPerLandblock} vertices, got {meshData.Vertices.Length}",
                nameof(meshData));
        if (meshData.Indices.Length != IndicesPerLandblock)
            throw new ArgumentException(
                $"Expected {IndicesPerLandblock} indices, got {meshData.Indices.Length}",
                nameof(meshData));

        if (_idToSlot.ContainsKey(landblockId))
            RemoveLandblock(landblockId);

        int slot = _alloc.Allocate(out var needsGrow);
        if (needsGrow)
        {
            int newCap = Math.Max(_alloc.Capacity * 2, slot + 1);
            EnsureCapacity(newCap);
        }

        // Bake worldOrigin into vertex positions; capture min/max Z for AABB.
        var bakedVerts = new TerrainVertex[VertsPerLandblock];
        float zMin = float.MaxValue, zMax = float.MinValue;
        for (int i = 0; i < VertsPerLandblock; i++)
        {
            var v = meshData.Vertices[i];
            var worldPos = v.Position + worldOrigin;
            bakedVerts[i] = new TerrainVertex(worldPos, v.Normal, v.Data0, v.Data1, v.Data2, v.Data3);
            if (worldPos.Z < zMin) zMin = worldPos.Z;
            if (worldPos.Z > zMax) zMax = worldPos.Z;
        }
        if (zMin == float.MaxValue) { zMin = 0f; zMax = 0f; }

        // Bake baseVertex into indices on the CPU side (driver-portable pattern).
        uint baseVertex = (uint)(slot * VertsPerLandblock);
        var bakedIndices = new uint[IndicesPerLandblock];
        for (int i = 0; i < IndicesPerLandblock; i++)
            bakedIndices[i] = meshData.Indices[i] + baseVertex;

        // glBufferSubData into the slot's VBO + EBO regions.
        nint vboByteOffset = (nint)(slot * VertsPerLandblock * VertexSize);
        nint eboByteOffset = (nint)(slot * IndicesPerLandblock * IndexSize);

        _gl.BindBuffer(BufferTargetARB.ArrayBuffer, _globalVbo);
        fixed (TerrainVertex* p = bakedVerts)
        {
            _gl.BufferSubData(BufferTargetARB.ArrayBuffer, vboByteOffset,
                (nuint)(VertsPerLandblock * VertexSize), p);
        }
        _gl.BindBuffer(BufferTargetARB.ArrayBuffer, 0);

        _gl.BindBuffer(BufferTargetARB.ElementArrayBuffer, _globalEbo);
        fixed (uint* p = bakedIndices)
        {
            _gl.BufferSubData(BufferTargetARB.ElementArrayBuffer, eboByteOffset,
                (nuint)(IndicesPerLandblock * IndexSize), p);
        }
        _gl.BindBuffer(BufferTargetARB.ElementArrayBuffer, 0);

        _slots[slot] = new SlotData
        {
            LandblockId = landblockId,
            WorldOrigin = worldOrigin,
            FirstIndex  = (uint)(slot * IndicesPerLandblock),
            IndexCount  = IndicesPerLandblock,
            AabbMin = new Vector3(worldOrigin.X, worldOrigin.Y, zMin),
            AabbMax = new Vector3(worldOrigin.X + LandblockSize, worldOrigin.Y + LandblockSize, zMax),
        };
        _idToSlot[landblockId] = slot;
    }

    public void RemoveLandblock(uint landblockId)
    {
        if (!_idToSlot.TryGetValue(landblockId, out var slot))
            return;
        _idToSlot.Remove(landblockId);
        _slots[slot] = null;
        _alloc.Free(slot);
        // No GPU clear: the per-frame DEIC array won't reference this slot.
    }

    public void Draw(ICamera camera, FrustumPlanes? frustum = null, uint? neverCullLandblockId = null)
    {
        if (_alloc.LoadedCount == 0) return;

        // Build visible slot list with per-slot frustum cull.
        _visibleSlots.Clear();
        for (int slot = 0; slot < _slots.Length; slot++)
        {
            var data = _slots[slot];
            if (data is null) continue;
            if (frustum is not null && data.LandblockId != neverCullLandblockId)
            {
                if (!FrustumCuller.IsAabbVisible(frustum.Value, data.AabbMin, data.AabbMax))
                    continue;
            }
            _visibleSlots.Add(slot);
        }
        if (_visibleSlots.Count == 0) return;

        // Build DEIC array.
        if (_deicScratch.Length < _visibleSlots.Count)
            _deicScratch = new DrawElementsIndirectCommand[Math.Max(_visibleSlots.Count, 64)];
        for (int i = 0; i < _visibleSlots.Count; i++)
        {
            var data = _slots[_visibleSlots[i]]!;
            _deicScratch[i] = new DrawElementsIndirectCommand
            {
                Count         = (uint)data.IndexCount,
                InstanceCount = 1u,
                FirstIndex    = data.FirstIndex,
                BaseVertex    = 0,            // baked into indices on upload
                BaseInstance  = 0,
            };
        }

        // Grow indirect buffer if needed.
        if (_visibleSlots.Count > _indirectCapacity)
        {
            _indirectCapacity = Math.Max(64, _visibleSlots.Count * 2);
            _gl.BindBuffer(GLEnum.DrawIndirectBuffer, _indirectBuffer);
            _gl.BufferData(GLEnum.DrawIndirectBuffer,
                (nuint)(_indirectCapacity * sizeof(DrawElementsIndirectCommand)),
                null, GLEnum.DynamicDraw);
        }
        else
        {
            _gl.BindBuffer(GLEnum.DrawIndirectBuffer, _indirectBuffer);
        }

        // Upload DEIC array.
        fixed (DrawElementsIndirectCommand* p = _deicScratch)
        {
            _gl.BufferSubData(GLEnum.DrawIndirectBuffer, 0,
                (nuint)(_visibleSlots.Count * sizeof(DrawElementsIndirectCommand)), p);
        }

        // Bind shader + uniforms + atlas handles.
        _shader.Use();
        _shader.SetMatrix4("uView", camera.View);
        _shader.SetMatrix4("uProjection", camera.Projection);

        var (terrainHandle, alphaHandle) = _atlas.GetBindlessHandles();
        // Pass each 64-bit handle as a uvec2 (low 32 bits, high 32 bits).
        // GLSL constructs sampler2DArray(uTerrainHandle) at the use site —
        // see terrain_modern.frag for why this is the safe pattern.
        _gl.ProgramUniform2(_shader.Program, _uTerrainHandleLoc,
            (uint)(terrainHandle & 0xFFFFFFFFu), (uint)(terrainHandle >> 32));
        _gl.ProgramUniform2(_shader.Program, _uAlphaHandleLoc,
            (uint)(alphaHandle   & 0xFFFFFFFFu), (uint)(alphaHandle   >> 32));

        _gl.BindVertexArray(_globalVao);
        _gl.MemoryBarrier(MemoryBarrierMask.CommandBarrierBit);
        _gl.MultiDrawElementsIndirect(
            PrimitiveType.Triangles, DrawElementsType.UnsignedInt,
            (void*)0,
            (uint)_visibleSlots.Count,
            (uint)sizeof(DrawElementsIndirectCommand));
        _gl.BindVertexArray(0);
        _gl.BindBuffer(GLEnum.DrawIndirectBuffer, 0);
    }

    public void Dispose()
    {
        _gl.DeleteVertexArray(_globalVao);
        _gl.DeleteBuffer(_globalVbo);
        _gl.DeleteBuffer(_globalEbo);
        _gl.DeleteBuffer(_indirectBuffer);
    }

    // ----------------------------------------------------------------
    // Private helpers
    // ----------------------------------------------------------------

    private void AllocateGpuBuffers(int capacitySlots)
    {
        nuint vboBytes = (nuint)(capacitySlots * VertsPerLandblock * VertexSize);
        nuint eboBytes = (nuint)(capacitySlots * IndicesPerLandblock * IndexSize);

        _gl.BindBuffer(BufferTargetARB.ArrayBuffer, _globalVbo);
        _gl.BufferData(BufferTargetARB.ArrayBuffer, vboBytes, null, BufferUsageARB.DynamicDraw);
        _gl.BindBuffer(BufferTargetARB.ArrayBuffer, 0);

        _gl.BindBuffer(BufferTargetARB.ElementArrayBuffer, _globalEbo);
        _gl.BufferData(BufferTargetARB.ElementArrayBuffer, eboBytes, null, BufferUsageARB.DynamicDraw);
        _gl.BindBuffer(BufferTargetARB.ElementArrayBuffer, 0);
    }

    private void ConfigureVao()
    {
        _gl.BindVertexArray(_globalVao);
        _gl.BindBuffer(BufferTargetARB.ArrayBuffer, _globalVbo);
        _gl.BindBuffer(BufferTargetARB.ElementArrayBuffer, _globalEbo);

        uint stride = (uint)VertexSize;

        // location 0: Position
        _gl.EnableVertexAttribArray(0);
        _gl.VertexAttribPointer(0, 3, VertexAttribPointerType.Float, false, stride, (void*)0);
        // location 1: Normal
        _gl.EnableVertexAttribArray(1);
        _gl.VertexAttribPointer(1, 3, VertexAttribPointerType.Float, false, stride, (void*)(3 * sizeof(float)));
        // locations 2-5: Data0..Data3 (uvec4 byte attributes)
        nint dataOffset = 6 * sizeof(float);
        _gl.EnableVertexAttribArray(2);
        _gl.VertexAttribIPointer(2, 4, VertexAttribIType.UnsignedByte, stride, (void*)dataOffset);
        _gl.EnableVertexAttribArray(3);
        _gl.VertexAttribIPointer(3, 4, VertexAttribIType.UnsignedByte, stride, (void*)(dataOffset + 4));
        _gl.EnableVertexAttribArray(4);
        _gl.VertexAttribIPointer(4, 4, VertexAttribIType.UnsignedByte, stride, (void*)(dataOffset + 8));
        _gl.EnableVertexAttribArray(5);
        _gl.VertexAttribIPointer(5, 4, VertexAttribIType.UnsignedByte, stride, (void*)(dataOffset + 12));

        _gl.BindVertexArray(0);
    }

    private void EnsureCapacity(int newCapacity)
    {
        if (newCapacity <= _alloc.Capacity) return;

        // Allocate new VBO + EBO at new size; copy old contents; swap; recreate VAO.
        uint newVbo = _gl.GenBuffer();
        uint newEbo = _gl.GenBuffer();

        nuint newVboBytes = (nuint)(newCapacity * VertsPerLandblock * VertexSize);
        nuint newEboBytes = (nuint)(newCapacity * IndicesPerLandblock * IndexSize);
        nuint oldVboBytes = (nuint)(_alloc.Capacity * VertsPerLandblock * VertexSize);
        nuint oldEboBytes = (nuint)(_alloc.Capacity * IndicesPerLandblock * IndexSize);

        _gl.BindBuffer(BufferTargetARB.ArrayBuffer, newVbo);
        _gl.BufferData(BufferTargetARB.ArrayBuffer, newVboBytes, null, BufferUsageARB.DynamicDraw);
        _gl.BindBuffer(BufferTargetARB.CopyReadBuffer, _globalVbo);
        _gl.BindBuffer(BufferTargetARB.CopyWriteBuffer, newVbo);
        _gl.CopyBufferSubData(CopyBufferSubDataTarget.CopyReadBuffer, CopyBufferSubDataTarget.CopyWriteBuffer,
            0, 0, oldVboBytes);
        _gl.DeleteBuffer(_globalVbo);
        _globalVbo = newVbo;

        _gl.BindBuffer(BufferTargetARB.ElementArrayBuffer, newEbo);
        _gl.BufferData(BufferTargetARB.ElementArrayBuffer, newEboBytes, null, BufferUsageARB.DynamicDraw);
        _gl.BindBuffer(BufferTargetARB.CopyReadBuffer, _globalEbo);
        _gl.BindBuffer(BufferTargetARB.CopyWriteBuffer, newEbo);
        _gl.CopyBufferSubData(CopyBufferSubDataTarget.CopyReadBuffer, CopyBufferSubDataTarget.CopyWriteBuffer,
            0, 0, oldEboBytes);
        _gl.DeleteBuffer(_globalEbo);
        _globalEbo = newEbo;

        // Recreate VAO with new buffer bindings.
        _gl.DeleteVertexArray(_globalVao);
        _globalVao = _gl.GenVertexArray();
        ConfigureVao();

        // Grow slot tracking array.
        Array.Resize(ref _slots, newCapacity);
        _alloc.GrowTo(newCapacity);
    }

    private sealed class SlotData
    {
        public uint    LandblockId;
        public Vector3 WorldOrigin;
        public uint    FirstIndex;
        public int     IndexCount;
        public Vector3 AabbMin;
        public Vector3 AabbMax;
    }
}