// ClipFrame.cs
//
// Phase U.3: the GPU-side container + uploader for the SHARED per-frame clip
// data consumed by mesh_modern.vert (SSBO binding=2) and terrain_modern.vert
// (UBO binding=2). This is the "shared" half of the U.3 clip mechanism; the
// per-instance slot index buffer (SSBO binding=3) is PER-RENDERER and owned by
// each renderer (WbDrawDispatcher / EnvCellRenderer), parallel to its instance
// buffer — it is NOT here.
//
// === The contract (both shader sides obey) ===================================
// binding=2 mesh SSBO holds an array of CellClip, one per "slot":
//     struct CellClip { uint count; uint _p0; uint _p1; uint _p2; vec4 planes[8]; };
//   std430 layout: count at byte 0, three pad uints at 4/8/12, planes[8] at 16
//   (vec4 stride 16) → 144 bytes per slot. Slot 0 is RESERVED = no-clip (count 0).
// binding=2 terrain UBO holds the single OutsideView region:
//     layout(std140) { int uTerrainClipCount; vec4 uTerrainClipPlanes[8]; };
//   std140 layout: count at byte 0 (padded to 16), planes[8] at 16 → 144 bytes.
//
// In U.3 a ClipFrame is built via NoClip(): one slot (slot 0, count 0) and a
// terrain count of 0. Everything renders exactly as before. U.4 populates real
// slots from a PortalVisibilityFrame (one CellClip per visible cell) and sets the
// terrain OutsideView planes, then points each renderer's per-instance slot
// buffer at the right slots.
//
// Pure CPU byte-packing + a thin GL upload. NO GL types appear except in
// UploadShared. The byte layout is asserted by ClipFrameLayoutTests so a silent
// std430/std140 drift can't reach the GPU.
using System;
using System.Collections.Generic;
using System.Numerics;
using Silk.NET.OpenGL;

namespace AcDream.App.Rendering;

/// <summary>
/// Per-frame container + uploader for the SHARED clip data: the binding=2 mesh
/// SSBO (one <c>CellClip</c> per slot, slot 0 reserved no-clip) and the binding=2
/// terrain UBO (the single OutsideView region). See the file header for the exact
/// std430 / std140 byte layout. Per-instance slot buffers (binding=3) are owned by
/// each renderer, not here.
/// </summary>
public sealed class ClipFrame : IDisposable
{
    // ---- Layout constants (mirror mesh_modern.vert + terrain_modern.vert) ----

    /// <summary>Max planes per clip region — matches the shader's <c>planes[8]</c>
    /// and GL's guaranteed <c>GL_MAX_CLIP_DISTANCES &gt;= 8</c>.</summary>
    public const int MaxPlanes = 8;

    /// <summary>std430 stride of one <c>CellClip</c>: 16 (count + 3 pad uints) +
    /// 8 × 16 (vec4 planes) = 144 bytes.</summary>
    public const int CellClipStrideBytes = 16 + MaxPlanes * 16; // 144

    /// <summary>Byte offset of <c>planes[0]</c> within a <c>CellClip</c> (after the
    /// count + 3 pad uints).</summary>
    public const int CellClipPlanesOffset = 16;

    /// <summary>std140 size of the terrain UBO block: int count padded to 16, then
    /// 8 × 16 (vec4 planes) = 144 bytes. Same number as the SSBO stride by
    /// coincidence of the 16-byte vec4 rule, but a DIFFERENT layout family.</summary>
    public const int TerrainUboBytes = 16 + MaxPlanes * 16; // 144

    /// <summary>SSBO binding index for the shared per-cell clip regions
    /// (mesh_modern.vert binding=2).</summary>
    public const uint MeshClipSsboBinding = 2;

    /// <summary>UBO binding index for the terrain OutsideView clip region
    /// (terrain_modern.vert binding=2). UBO namespace — distinct from the SSBO
    /// binding=2 above.</summary>
    public const uint TerrainClipUboBinding = 2;

    // ---- CPU-side state ------------------------------------------------------

    // Packed std430 bytes for clipRegions[]. Always holds at least slot 0.
    private byte[] _regionBytes;
    private int _slotCount;

    // Packed std140 bytes for the terrain UBO (always TerrainUboBytes long).
    private readonly byte[] _terrainBytes = new byte[TerrainUboBytes];

    // ---- GL-side state (lazily created on first UploadShared) ----------------

    private uint _regionSsbo;
    private uint _terrainUbo;
    private bool _glInitialized;
    private bool _disposed;

    // GL reference captured on the first UploadShared so Dispose can delete the two
    // buffers. ClipFrame is long-lived in U.3 (GameWindow holds one via ??= NoClip()
    // and reuses it every frame), so we DO own buffer teardown — see Dispose.
    private GL? _gl;

    private ClipFrame(byte[] regionBytes, int slotCount)
    {
        _regionBytes = regionBytes;
        _slotCount = slotCount;
        // Terrain defaults to count 0 (ungated). _terrainBytes is already all
        // zeros, which encodes count=0 + zeroed (unused) planes.
    }

    /// <summary>
    /// The U.3 default frame: exactly slot 0 (no-clip, count 0) and a terrain
    /// count of 0. The whole scene renders ungated — identical to pre-U.3. U.4
    /// replaces this with a frame built from real portal visibility.
    /// </summary>
    public static ClipFrame NoClip()
    {
        // One slot, all zeros: count=0 ⇒ shader passes every plane.
        var bytes = new byte[CellClipStrideBytes];
        return new ClipFrame(bytes, slotCount: 1);
    }

    /// <summary>Number of clip slots currently packed (always &gt;= 1 — slot 0 is
    /// the reserved no-clip slot).</summary>
    public int SlotCount => _slotCount;

    /// <summary>
    /// Phase U.4: reset this frame back to the NoClip state — exactly slot 0
    /// (no-clip, count 0) and a terrain count of 0 — WITHOUT allocating a new
    /// frame or new GL buffers. The single long-lived <c>_clipFrame</c> in
    /// GameWindow is reset + re-packed every frame by <see cref="ClipFrameAssembler"/>,
    /// then re-uploaded via <see cref="UploadShared"/> (which reuses the same SSBO /
    /// UBO ids). This keeps the per-frame cost at one BufferData per buffer instead
    /// of leaking a fresh pair of GL buffers each frame.
    /// </summary>
    public void Reset()
    {
        // Slot 0 = no-clip (count 0). Zero just the slot-0 region; the tail beyond
        // _slotCount is never uploaded, so it needn't be cleared. AppendSlot writes
        // each new slot's count + planes in full, so stale bytes there are
        // overwritten before they can be uploaded.
        if (_regionBytes.Length < CellClipStrideBytes)
            EnsureRegionCapacity(CellClipStrideBytes);
        Array.Clear(_regionBytes, 0, CellClipStrideBytes);
        _slotCount = 1;

        // Terrain back to count 0 (ungated) until SetTerrainClip is called again.
        Array.Clear(_terrainBytes);
    }

    /// <summary>The shared mesh-clip SSBO id, or 0 before the first
    /// <see cref="UploadShared"/>. Renderers may bind this directly if they don't
    /// receive it via a parameter; <see cref="UploadShared"/> already binds it to
    /// <see cref="MeshClipSsboBinding"/>.</summary>
    public uint RegionSsbo => _regionSsbo;

    /// <summary>The terrain-clip UBO id, or 0 before the first
    /// <see cref="UploadShared"/>. Handed to <see cref="TerrainModernRenderer"/>
    /// so it can re-bind binding=2 (UBO namespace) before its draw.</summary>
    public uint TerrainUbo => _terrainUbo;

    /// <summary>
    /// Append one clip region (becomes the next slot index) from a
    /// <see cref="ClipPlaneSet"/>. Only the convex-plane case is supported in
    /// U.3 — <c>Count &gt; 0</c> packs that many planes; <c>Count == 0</c> packs a
    /// no-clip region (pass-all). The scissor / nothing-visible fallbacks that
    /// <see cref="ClipPlaneSet"/> can carry are deferred to U.4 (which will draw
    /// the AABB box or skip the cell on the CPU side, not via this slot). Returns
    /// the new slot's index.
    /// </summary>
    public int AppendSlot(ClipPlaneSet set)
    {
        int count = Math.Min(set.Count, MaxPlanes);
        if (count == 0)
            return AppendSlot(ReadOnlySpan<Vector4>.Empty);

        Span<Vector4> planes = stackalloc Vector4[count];
        for (int i = 0; i < count; i++)
            planes[i] = set.Planes[i];
        return AppendSlot(planes);
    }

    /// <summary>
    /// Append one clip region from a raw plane list. <paramref name="planes"/>
    /// length 0 packs a no-clip (pass-all) region; otherwise up to
    /// <see cref="MaxPlanes"/> planes are packed (extras ignored). Each plane is
    /// <c>(nx, ny, 0, dw)</c> in clip space; a clip-space vertex is inside iff
    /// <c>dot(plane, gl_Position) &gt;= 0</c> for every plane. Returns the new
    /// slot index.
    /// </summary>
    public int AppendSlot(ReadOnlySpan<Vector4> planes)
    {
        int count = Math.Min(planes.Length, MaxPlanes);

        int slot = _slotCount;
        int byteOffset = slot * CellClipStrideBytes;
        EnsureRegionCapacity(byteOffset + CellClipStrideBytes);

        // count (uint) at byteOffset; the 3 pad uints stay zero.
        WriteUInt(_regionBytes, byteOffset, (uint)count);

        for (int i = 0; i < count; i++)
        {
            int po = byteOffset + CellClipPlanesOffset + i * 16;
            WriteVec4(_regionBytes, po, planes[i]);
        }

        _slotCount++;
        return slot;
    }

    /// <summary>
    /// Set the terrain OutsideView clip region (the single region the terrain
    /// shader gates against). <paramref name="planes"/> length 0 ungates terrain
    /// (count 0). U.3 callers never touch this — <see cref="NoClip"/> leaves it
    /// at count 0. U.4 calls it with the OutsideView planes.
    /// </summary>
    public void SetTerrainClip(ReadOnlySpan<Vector4> planes)
    {
        int count = Math.Min(planes.Length, MaxPlanes);
        Array.Clear(_terrainBytes);
        WriteInt(_terrainBytes, 0, count);
        for (int i = 0; i < count; i++)
            WriteVec4(_terrainBytes, CellClipPlanesOffset + i * 16, planes[i]);
    }

    /// <summary>
    /// Upload the shared mesh-clip SSBO (binding=2) and the terrain-clip UBO
    /// (binding=2, UBO namespace) and bind both to their binding points. Idempotent
    /// to call once per frame. Creates the GL buffers lazily on first call.
    /// </summary>
    public unsafe void UploadShared(GL gl)
    {
        ArgumentNullException.ThrowIfNull(gl);
        ObjectDisposedException.ThrowIf(_disposed, this);

        if (!_glInitialized)
        {
            _gl = gl; // captured for Dispose (single context for the frame's lifetime)
            _regionSsbo = gl.GenBuffer();
            _terrainUbo = gl.GenBuffer();
            _glInitialized = true;
        }

        int regionByteCount = _slotCount * CellClipStrideBytes;
        gl.BindBuffer(BufferTargetARB.ShaderStorageBuffer, _regionSsbo);
        fixed (byte* p = _regionBytes)
        {
            gl.BufferData(BufferTargetARB.ShaderStorageBuffer,
                (nuint)regionByteCount, p, BufferUsageARB.DynamicDraw);
        }
        gl.BindBufferBase(BufferTargetARB.ShaderStorageBuffer, MeshClipSsboBinding, _regionSsbo);

        gl.BindBuffer(BufferTargetARB.UniformBuffer, _terrainUbo);
        fixed (byte* p = _terrainBytes)
        {
            gl.BufferData(BufferTargetARB.UniformBuffer,
                (nuint)TerrainUboBytes, p, BufferUsageARB.DynamicDraw);
        }
        gl.BindBufferBase(BufferTargetARB.UniformBuffer, TerrainClipUboBinding, _terrainUbo);
    }

    public void Dispose()
    {
        if (_disposed) return;
        _disposed = true;
        // ClipFrame is long-lived in U.3 (GameWindow holds one via ??= NoClip() and
        // reuses it every frame), so we own the two GL buffers and delete them here.
        // _glInitialized guards the case where UploadShared never ran (no buffers to
        // delete, and _gl was never captured).
        if (_glInitialized && _gl is not null)
        {
            _gl.DeleteBuffer(_regionSsbo);
            _gl.DeleteBuffer(_terrainUbo);
            _regionSsbo = 0;
            _terrainUbo = 0;
        }
    }

    // ---- byte helpers (little-endian; matches x86/x64 GPU upload) ------------

    private void EnsureRegionCapacity(int requiredBytes)
    {
        if (_regionBytes.Length >= requiredBytes) return;
        int newLen = Math.Max(requiredBytes, _regionBytes.Length * 2);
        Array.Resize(ref _regionBytes, newLen);
    }

    private static void WriteUInt(byte[] dst, int offset, uint value)
    {
        dst[offset + 0] = (byte)(value & 0xFF);
        dst[offset + 1] = (byte)((value >> 8) & 0xFF);
        dst[offset + 2] = (byte)((value >> 16) & 0xFF);
        dst[offset + 3] = (byte)((value >> 24) & 0xFF);
    }

    private static void WriteInt(byte[] dst, int offset, int value)
        => WriteUInt(dst, offset, unchecked((uint)value));

    private static void WriteVec4(byte[] dst, int offset, Vector4 v)
    {
        WriteFloat(dst, offset + 0, v.X);
        WriteFloat(dst, offset + 4, v.Y);
        WriteFloat(dst, offset + 8, v.Z);
        WriteFloat(dst, offset + 12, v.W);
    }

    private static void WriteFloat(byte[] dst, int offset, float value)
    {
        uint bits = BitConverter.SingleToUInt32Bits(value);
        WriteUInt(dst, offset, bits);
    }

    // ---- Test seams ----------------------------------------------------------

    /// <summary>Test seam: the packed std430 region bytes (slot 0..SlotCount-1).
    /// Read-only snapshot used by ClipFrameLayoutTests to assert the byte layout.</summary>
    internal ReadOnlySpan<byte> RegionBytesForTest => _regionBytes.AsSpan(0, _slotCount * CellClipStrideBytes);

    /// <summary>Test seam: the packed std140 terrain UBO bytes.</summary>
    internal ReadOnlySpan<byte> TerrainBytesForTest => _terrainBytes;
}