// RayQueryPick — regression test for the WebGPU software ray-query shim.
//
// Builds an 8³ = 512-instance TLAS (well below the 8193 threshold where a
// hardcoded 16384-leaf TLAS start used to make every rayQuery pick miss —
// issue #25) and shoots ONE fully-determined ray through a `rayQuery=true`
// compute shader. The committed hit is read back to the host and checked
// against the analytically-known answer.
//
// The scene also renders through the wavefront RT pipeline (same as
// RTStress) so the run produces a visible frame, but the pass/fail signal
// is the console line printed from the read-back pick result.
//
// WebGPU/DOM only — the rayQuery shim is the WebGPU software RT path.

#ifndef CRAFTER_GRAPHICS_WINDOW_DOM
int main() { return 0; }   // native path uses hardware ray queries
#else

#include <cstdio>   // std::fflush / stdout — flush the verdict past _Exit

import Crafter.Graphics;
import Crafter.Math;
import Crafter.Event;
import std;

using namespace Crafter;
namespace fs = std::filesystem;

namespace {
    constexpr int   kGrid    = 8;       // 8³ = 512 instances (< 8193 ⇒ bug regime)
    constexpr float kSpacing = 2.5f;
    constexpr float kHalf    = 0.5f;

    // Analytically-known target: a -X ray down the (iy=4, iz=4) row hits the
    // cube with the largest X centre (ix=7) first.
    constexpr int kHitX = 7, kHitY = 4, kHitZ = 4;
    constexpr std::uint32_t kExpectedCustomIndex =
        static_cast<std::uint32_t>(((kHitX * kGrid) + kHitY) * kGrid + kHitZ); // 484

    struct CameraGPU {
        float origin[3];   float pad0;
        float right[3];    float tanHalf;
        float up[3];       float aspect;
        float forward[3];  float pad1;
    };
    static_assert(sizeof(CameraGPU) == 64);

    // @group(0) push for the pick shader: ray origin + direction.
    struct PickPush {
        float origin[3]; float pad0;
        float dir[3];    float pad1;
    };
    static_assert(sizeof(PickPush) == 32);

    struct PickResult {
        std::uint32_t hit;
        std::uint32_t instanceCustomIndex;
        std::uint32_t primitiveIndex;
        float         tHit;
    };
    static_assert(sizeof(PickResult) == 16);
}

int main() {
    const int instanceCount = kGrid * kGrid * kGrid;
    std::println("[RayQueryPick] grid {}^3 = {} instances (expected hit customIndex {})",
                 kGrid, instanceCount, kExpectedCustomIndex);

    Device::Initialize();
    static Window window(1280, 720, "RayQueryPick");
    auto cmd = window.StartInit();

    DescriptorHeapWebGPU heap;
    heap.Initialize(/*images*/ 1, /*buffers*/ 2, /*samplers*/ 1);

    std::array<WebGPUShader, 4> shaders {{
        WebGPUShader(fs::path("raygen.wgsl"),     "raygen_main",     WebGPURTStage::Raygen),
        WebGPUShader(fs::path("miss.wgsl"),       "miss_main",       WebGPURTStage::Miss),
        WebGPUShader(fs::path("closesthit.wgsl"), "closesthit_main", WebGPURTStage::ClosestHit),
        WebGPUShader(fs::path("resolve.wgsl"),    "resolve_main",    WebGPURTStage::Resolve),
    }};
    ShaderBindingTableWebGPU sbt;
    sbt.Init(shaders);

    std::array<RTShaderGroup, 1> raygenGroups {{ { .type = RTShaderGroupType::General,           .generalShader = 0 } }};
    std::array<RTShaderGroup, 1> missGroups   {{ { .type = RTShaderGroupType::General,           .generalShader = 1 } }};
    std::array<RTShaderGroup, 1> hitGroups    {{ { .type = RTShaderGroupType::TrianglesHitGroup, .closestHitShader = 2 } }};

    std::array<UICustomBinding, 1> bindings {{
        { .group = 3, .binding = 0, .kind = UICustomBindingKind::Buffer, ._pad = 0, .pushOffset = 0 },
    }};

    PipelineRTWebGPU pipeline;
    pipeline.Init(cmd, raygenGroups, missGroups, hitGroups, sbt, bindings);

    // ── Unit cube mesh (8 verts, 12 tris). ────────────────────────────
    static std::array<Vector<float, 3, 3>, 8> verts {{
        {-kHalf, -kHalf, -kHalf}, { kHalf, -kHalf, -kHalf},
        { kHalf,  kHalf, -kHalf}, {-kHalf,  kHalf, -kHalf},
        {-kHalf, -kHalf,  kHalf}, { kHalf, -kHalf,  kHalf},
        { kHalf,  kHalf,  kHalf}, {-kHalf,  kHalf,  kHalf},
    }};
    static std::array<std::uint32_t, 36> indices {{
        0,1,2, 0,2,3,   5,4,7, 5,7,6,   4,0,3, 4,3,7,
        1,5,6, 1,6,2,   4,5,1, 4,1,0,   3,2,6, 3,6,7,
    }};
    static Mesh cube;
    cube.Build(verts, indices, cmd);

    WebGPUBuffer<CameraGPU, true> cameraBuf;
    cameraBuf.Create(1);
    static std::array<std::uint32_t, 1> userHandles { cameraBuf.handle };

    // ── Instance grid. ─────────────────────────────────────────────────
    static std::vector<RenderingElement3D> renderers;
    renderers.reserve(static_cast<std::size_t>(instanceCount));
    const float origin0 = -0.5f * static_cast<float>(kGrid - 1) * kSpacing;
    for (int x = 0; x < kGrid; ++x)
    for (int y = 0; y < kGrid; ++y)
    for (int z = 0; z < kGrid; ++z) {
        renderers.emplace_back();
        RenderingElement3D& r = renderers.back();
        auto& tx = r.instance.transform.matrix;
        tx[0][0] = 1; tx[0][1] = 0; tx[0][2] = 0; tx[0][3] = origin0 + float(x) * kSpacing;
        tx[1][0] = 0; tx[1][1] = 1; tx[1][2] = 0; tx[1][3] = origin0 + float(y) * kSpacing;
        tx[2][0] = 0; tx[2][1] = 0; tx[2][2] = 1; tx[2][3] = origin0 + float(z) * kSpacing;
        r.instance.instanceCustomIndex                    = static_cast<std::uint32_t>(renderers.size() - 1);
        r.instance.mask                                   = 0xFF;
        r.instance.instanceShaderBindingTableRecordOffset = 0;
        r.instance.flags                                  = kRTGeometryInstanceForceOpaque;
        r.instance.accelerationStructureReference         = cube.blasAddr;
        RenderingElement3D::Add(&r);
    }
    RenderingElement3D::BuildTLAS(cmd, 0);

    window.descriptorHeap = &heap;
    window.FinishInit();

    RTPass rtPass(&pipeline);
    rtPass.handlesPtr   = userHandles.data();
    rtPass.handlesCount = static_cast<std::uint32_t>(userHandles.size());
    rtPass.maxDepth     = 1;
    window.passes.push_back(&rtPass);

    // Fixed camera framing the grid from a corner, aimed at the centre.
    {
        const float ext = float(kGrid - 1) * kSpacing;
        Vector<float, 3, 4> pos { ext * 1.4f, ext * 1.0f, ext * 1.4f };
        Vector<float, 3, 4> d { -pos.x, -pos.y, -pos.z };
        const float len = std::sqrt(d.x*d.x + d.y*d.y + d.z*d.z);
        Vector<float, 3, 4> forward { d.x/len, d.y/len, d.z/len };
        Vector<float, 3, 4> worldUp { 0.0f, 1.0f, 0.0f };
        Vector<float, 3, 4> right { forward.y*worldUp.z - forward.z*worldUp.y,
                                    forward.z*worldUp.x - forward.x*worldUp.z,
                                    forward.x*worldUp.y - forward.y*worldUp.x };
        const float rLen = std::sqrt(right.x*right.x + right.y*right.y + right.z*right.z);
        right.x /= rLen; right.y /= rLen; right.z /= rLen;
        Vector<float, 3, 4> up { right.y*forward.z - right.z*forward.y,
                                 right.z*forward.x - right.x*forward.z,
                                 right.x*forward.y - right.y*forward.x };
        CameraGPU& g = cameraBuf.value[0];
        g.origin[0]=pos.x; g.origin[1]=pos.y; g.origin[2]=pos.z; g.pad0=0;
        g.right[0]=right.x;   g.right[1]=right.y;   g.right[2]=right.z;
        g.up[0]=up.x;         g.up[1]=up.y;         g.up[2]=up.z;
        g.forward[0]=forward.x; g.forward[1]=forward.y; g.forward[2]=forward.z;
        g.aspect  = float(window.width) / float(window.height);
        g.tanHalf = std::tan(70.0f * 3.14159265f / 360.0f);
        g.pad1    = 0;
        cameraBuf.FlushDevice();
    }

    // ── rayQuery pick shader + output buffer. ──────────────────────────
    static PlainComputeShader pickShader;
    std::array<UICustomBinding, 1> pickBindings {{
        { .group = 2, .binding = 0, .kind = UICustomBindingKind::BufferReadWrite, ._pad = 0, .pushOffset = 0 },
    }};
    pickShader.Load(fs::path("rayquery_pick.wgsl"),
                    static_cast<std::uint32_t>(sizeof(PickPush)),
                    pickBindings, /*rayQuery*/ true);

    static WebGPUBuffer<PickResult, true> pickBuf;
    pickBuf.Create(1);
    static std::array<std::uint32_t, 1> pickHandles { pickBuf.handle };

    // The known ray: -X down the (iy,iz) row, far enough out to clear the grid.
    static PickPush push {};
    push.origin[0] = 50.0f;
    push.origin[1] = origin0 + float(kHitY) * kSpacing;
    push.origin[2] = origin0 + float(kHitZ) * kSpacing;
    push.dir[0]    = -1.0f; push.dir[1] = 0.0f; push.dir[2] = 0.0f;

    static int  frame      = 0;
    static bool dispatched = false;
    static bool reported   = false;
    EventListener<void> tick(&window.onBeforeUpdate, [&]() {
        if (reported) return;
        // Let a couple of frames go by so the TLAS build has certainly run.
        if (frame == 2 && !dispatched) {
            pickShader.Dispatch(&push, sizeof(push), pickHandles, 1, 1, 1);
            pickBuf.EnqueueReadback();
            dispatched = true;
        } else if (dispatched && pickBuf.PollReadback()) {
            const PickResult& r = pickBuf.value[0];
            const bool ok = (r.hit == 1u) && (r.instanceCustomIndex == kExpectedCustomIndex);
            std::println("[RayQueryPick] result: hit={} customIndex={} prim={} t={}",
                         r.hit, r.instanceCustomIndex, r.primitiveIndex, r.tHit);
            if (ok) {
                std::println("[RayQueryPick] PASS — rayQuery TLAS traversal hit the expected instance");
            } else {
                std::println("[RayQueryPick] FAIL — expected hit=1 customIndex={}, got hit={} customIndex={}",
                             kExpectedCustomIndex, r.hit, r.instanceCustomIndex);
            }
            // The render loop runs after main's _Exit, where stdio is never
            // flushed implicitly — push the verdict out explicitly.
            std::fflush(stdout);
            reported = true;
        }
        ++frame;
    });

    window.Render();
    window.StartUpdate();
    window.StartSync();
    return 0;
}
#endif