use std::iter;

use cgmath::prelude::*;
use wgpu::util::DeviceExt;
use winit::{
    event::*,
    event_loop::{ControlFlow, EventLoop},
    window::{Window, WindowBuilder},
};

mod texture;

#[repr(C)]
#[derive(Copy, Clone, Debug, bytemuck::Pod, bytemuck::Zeroable)]
struct Vertex {
    position: [f32; 3],
    tex_coords: [f32; 2],
}

impl Vertex {
    fn desc<'a>() -> wgpu::VertexBufferLayout<'a> {
        use std::mem;
        wgpu::VertexBufferLayout {
            array_stride: mem::size_of::<Vertex>() as wgpu::BufferAddress,
            step_mode: wgpu::InputStepMode::Vertex,
            attributes: &[
                wgpu::VertexAttribute {
                    offset: 0,
                    shader_location: 0,
                    format: wgpu::VertexFormat::Float32x3,
                },
                wgpu::VertexAttribute {
                    offset: mem::size_of::<[f32; 3]>() as wgpu::BufferAddress,
                    shader_location: 1,
                    format: wgpu::VertexFormat::Float32x2,
                },
            ],
        }
    }
}

const VERTICES: &[Vertex] = &[
    Vertex {
        position: [-0.0868241, -0.49240386, 0.0],
        tex_coords: [1.0 - 0.4131759, 1.0 - 0.00759614],
    }, // A
    Vertex {
        position: [-0.49513406, -0.06958647, 0.0],
        tex_coords: [1.0 - 0.0048659444, 1.0 - 0.43041354],
    }, // B
    Vertex {
        position: [-0.21918549, 0.44939706, 0.0],
        tex_coords: [1.0 - 0.28081453, 1.0 - 0.949397057],
    }, // C
    Vertex {
        position: [0.35966998, 0.3473291, 0.0],
        tex_coords: [1.0 - 0.85967, 1.0 - 0.84732911],
    }, // D
    Vertex {
        position: [0.44147372, -0.2347359, 0.0],
        tex_coords: [1.0 - 0.9414737, 1.0 - 0.2652641],
    }, // E
];

const INDICES: &[u16] = &[0, 1, 4, 1, 2, 4, 2, 3, 4, /* padding */ 0];

#[rustfmt::skip]
pub const OPENGL_TO_WGPU_MATRIX: cgmath::Matrix4<f32> = cgmath::Matrix4::new(
    1.0, 0.0, 0.0, 0.0,
    0.0, 1.0, 0.0, 0.0,
    0.0, 0.0, 0.5, 0.0,
    0.0, 0.0, 0.5, 1.0,
);

const NUM_INSTANCES_PER_ROW: u32 = 10;
const INSTANCE_DISPLACEMENT: cgmath::Vector3<f32> = cgmath::Vector3::new(
    NUM_INSTANCES_PER_ROW as f32 * 0.5,
    0.0,
    NUM_INSTANCES_PER_ROW as f32 * 0.5,
);

struct Camera {
    eye: cgmath::Point3<f32>,
    target: cgmath::Point3<f32>,
    up: cgmath::Vector3<f32>,
    aspect: f32,
    fovy: f32,
    znear: f32,
    zfar: f32,
}

impl Camera {
    fn build_view_projection_matrix(&self) -> cgmath::Matrix4<f32> {
        let view = cgmath::Matrix4::look_at_rh(self.eye, self.target, self.up);
        let proj = cgmath::perspective(cgmath::Deg(self.fovy), self.aspect, self.znear, self.zfar);
        proj * view
    }
}

#[repr(C)]
#[derive(Copy, Clone, bytemuck::Pod, bytemuck::Zeroable)]
struct Uniforms {
    view_proj: [[f32; 4]; 4],
}

impl Uniforms {
    fn new() -> Self {
        Self {
            view_proj: cgmath::Matrix4::identity().into(),
        }
    }

    fn update_view_proj(&mut self, camera: &Camera) {
        self.view_proj = (OPENGL_TO_WGPU_MATRIX * camera.build_view_projection_matrix()).into();
    }
}

struct CameraController {
    speed: f32,
    is_up_pressed: bool,
    is_down_pressed: bool,
    is_forward_pressed: bool,
    is_backward_pressed: bool,
    is_left_pressed: bool,
    is_right_pressed: bool,
}

impl CameraController {
    fn new(speed: f32) -> Self {
        Self {
            speed,
            is_up_pressed: false,
            is_down_pressed: false,
            is_forward_pressed: false,
            is_backward_pressed: false,
            is_left_pressed: false,
            is_right_pressed: false,
        }
    }

    fn process_events(&mut self, event: &WindowEvent) -> bool {
        match event {
            WindowEvent::KeyboardInput {
                input:
                    KeyboardInput {
                        state,
                        virtual_keycode: Some(keycode),
                        ..
                    },
                ..
            } => {
                let is_pressed = *state == ElementState::Pressed;
                match keycode {
                    VirtualKeyCode::Space => {
                        self.is_up_pressed = is_pressed;
                        true
                    }
                    VirtualKeyCode::LShift => {
                        self.is_down_pressed = is_pressed;
                        true
                    }
                    VirtualKeyCode::W | VirtualKeyCode::Up => {
                        self.is_forward_pressed = is_pressed;
                        true
                    }
                    VirtualKeyCode::A | VirtualKeyCode::Left => {
                        self.is_left_pressed = is_pressed;
                        true
                    }
                    VirtualKeyCode::S | VirtualKeyCode::Down => {
                        self.is_backward_pressed = is_pressed;
                        true
                    }
                    VirtualKeyCode::D | VirtualKeyCode::Right => {
                        self.is_right_pressed = is_pressed;
                        true
                    }
                    _ => false,
                }
            }
            _ => false,
        }
    }

    fn update_camera(&self, camera: &mut Camera) {
        let forward = camera.target - camera.eye;
        let forward_norm = forward.normalize();
        let forward_mag = forward.magnitude();

        // Prevents glitching when camera gets too close to the
        // center of the scene.
        if self.is_forward_pressed && forward_mag > self.speed {
            camera.eye += forward_norm * self.speed;
        }
        if self.is_backward_pressed {
            camera.eye -= forward_norm * self.speed;
        }

        let right = forward_norm.cross(camera.up);

        // Redo radius calc in case the up/ down is pressed.
        let forward = camera.target - camera.eye;
        let forward_mag = forward.magnitude();

        if self.is_right_pressed {
            // Rescale the distance between the target and eye so
            // that it doesn't change. The eye therefore still
            // lies on the circle made by the target and eye.
            camera.eye = camera.target - (forward + right * self.speed).normalize() * forward_mag;
        }
        if self.is_left_pressed {
            camera.eye = camera.target - (forward - right * self.speed).normalize() * forward_mag;
        }
    }
}

const ROTATION_SPEED: f32 = 2.0 * std::f32::consts::PI / 60.0;

struct Instance {
    position: cgmath::Vector3<f32>,
    rotation: cgmath::Quaternion<f32>,
}

impl Instance {
    fn to_raw(&self) -> InstanceRaw {
        let transform =
            cgmath::Matrix4::from_translation(self.position) * cgmath::Matrix4::from(self.rotation);
        InstanceRaw {
            transform: transform.into(),
        }
    }
}

#[repr(C)]
#[derive(Copy, Clone, Debug, bytemuck::Pod, bytemuck::Zeroable)]
struct InstanceRaw {
    transform: [[f32; 4]; 4],
}

impl InstanceRaw {
    fn desc<'a>() -> wgpu::VertexBufferLayout<'a> {
        use std::mem;
        wgpu::VertexBufferLayout {
            array_stride: mem::size_of::<InstanceRaw>() as wgpu::BufferAddress,
            // We need to switch from using a step mode of Vertex to Instance
            // This means that our shaders will only change to use the next
            // instance when the shader starts processing a new instance
            step_mode: wgpu::InputStepMode::Instance,
            attributes: &[
                wgpu::VertexAttribute {
                    offset: 0,
                    // While our vertex shader only uses locations 0, and 1 now, in later tutorials we'll
                    // be using 2, 3, and 4, for Vertex. We'll start at slot 5 not conflict with them later
                    shader_location: 5,
                    format: wgpu::VertexFormat::Float32x4,
                },
                // A mat4 takes up 4 vertex slots as it is technically 4 vec4s. We need to define a slot
                // for each vec4. We don't have to do this in code though.
                wgpu::VertexAttribute {
                    offset: mem::size_of::<[f32; 4]>() as wgpu::BufferAddress,
                    shader_location: 6,
                    format: wgpu::VertexFormat::Float32x4,
                },
                wgpu::VertexAttribute {
                    offset: mem::size_of::<[f32; 8]>() as wgpu::BufferAddress,
                    shader_location: 7,
                    format: wgpu::VertexFormat::Float32x4,
                },
                wgpu::VertexAttribute {
                    offset: mem::size_of::<[f32; 12]>() as wgpu::BufferAddress,
                    shader_location: 8,
                    format: wgpu::VertexFormat::Float32x4,
                },
            ],
        }
    }
}

struct State {
    surface: wgpu::Surface,
    device: wgpu::Device,
    queue: wgpu::Queue,
    sc_desc: wgpu::SwapChainDescriptor,
    swap_chain: wgpu::SwapChain,
    render_pipeline: wgpu::RenderPipeline,
    vertex_buffer: wgpu::Buffer,
    index_buffer: wgpu::Buffer,
    num_indices: u32,
    #[allow(dead_code)]
    diffuse_texture: texture::Texture,
    diffuse_bind_group: wgpu::BindGroup,
    camera: Camera,
    camera_controller: CameraController,
    uniforms: Uniforms,
    uniform_buffer: wgpu::Buffer,
    uniform_bind_group: wgpu::BindGroup,
    size: winit::dpi::PhysicalSize<u32>,
    instances: Vec<Instance>,
    instance_buffer: wgpu::Buffer,
}

fn quat_mul(q: cgmath::Quaternion<f32>, r: cgmath::Quaternion<f32>) -> cgmath::Quaternion<f32> {
    // This block uses quaternions of the form of

    // q=q0+iq1+jq2+kq3

    // and

    // r=r0+ir1+jr2+kr3.

    // The quaternion product has the form of

    // t=q×r=t0+it1+jt2+kt3,

    // where

    // t0=(r0 q0 − r1 q1 − r2 q2 − r3 q3)
    // t1=(r0 q1 + r1 q0 − r2 q3 + r3 q2)
    // t2=(r0 q2 + r1 q3 + r2 q0 − r3 q1)
    // t3=(r0 q3 − r1 q2 + r2 q1 + r3 q0

    let w = r.s * q.s - r.v.x * q.v.x - r.v.y * q.v.y - r.v.z * q.v.z;
    let xi = r.s * q.v.x + r.v.x * q.s - r.v.y * q.v.z + r.v.z * q.v.y;
    let yj = r.s * q.v.y + r.v.x * q.v.z + r.v.y * q.s - r.v.z * q.v.x;
    let zk = r.s * q.v.z - r.v.x * q.v.y + r.v.y * q.v.x + r.v.z * q.s;

    cgmath::Quaternion::new(w, xi, yj, zk)
}

impl State {
    async fn new(window: &Window) -> Self {
        let size = window.inner_size();

        // The instance is a handle to our GPU
        // BackendBit::PRIMARY => Vulkan + Metal + DX12 + Browser WebGPU
        let instance = wgpu::Instance::new(wgpu::BackendBit::PRIMARY);
        let surface = unsafe { instance.create_surface(window) };
        let adapter = instance
            .request_adapter(&wgpu::RequestAdapterOptions {
                power_preference: wgpu::PowerPreference::default(),
                compatible_surface: Some(&surface),
            })
            .await
            .unwrap();
        let (device, queue) = adapter
            .request_device(
                &wgpu::DeviceDescriptor {
                    label: None,
                    features: wgpu::Features::empty(),
                    limits: wgpu::Limits::default(),
                },
                None, // Trace path
            )
            .await
            .unwrap();

        let sc_desc = wgpu::SwapChainDescriptor {
            usage: wgpu::TextureUsage::RENDER_ATTACHMENT,
            format: adapter.get_swap_chain_preferred_format(&surface).unwrap(),
            width: size.width,
            height: size.height,
            present_mode: wgpu::PresentMode::Fifo,
        };
        let swap_chain = device.create_swap_chain(&surface, &sc_desc);

        let diffuse_bytes = include_bytes!("happy-tree.png");
        let diffuse_texture =
            texture::Texture::from_bytes(&device, &queue, diffuse_bytes, "happy-tree.png").unwrap();

        let texture_bind_group_layout =
            device.create_bind_group_layout(&wgpu::BindGroupLayoutDescriptor {
                entries: &[
                    wgpu::BindGroupLayoutEntry {
                        binding: 0,
                        visibility: wgpu::ShaderStage::FRAGMENT,
                        ty: wgpu::BindingType::Texture {
                            multisampled: false,
                            view_dimension: wgpu::TextureViewDimension::D2,
                            sample_type: wgpu::TextureSampleType::Float { filterable: true },
                        },
                        count: None,
                    },
                    wgpu::BindGroupLayoutEntry {
                        binding: 1,
                        visibility: wgpu::ShaderStage::FRAGMENT,
                        ty: wgpu::BindingType::Sampler {
                            comparison: false,
                            filtering: true,
                        },
                        count: None,
                    },
                ],
                label: Some("texture_bind_group_layout"),
            });

        let diffuse_bind_group = device.create_bind_group(&wgpu::BindGroupDescriptor {
            layout: &texture_bind_group_layout,
            entries: &[
                wgpu::BindGroupEntry {
                    binding: 0,
                    resource: wgpu::BindingResource::TextureView(&diffuse_texture.view),
                },
                wgpu::BindGroupEntry {
                    binding: 1,
                    resource: wgpu::BindingResource::Sampler(&diffuse_texture.sampler),
                },
            ],
            label: Some("diffuse_bind_group"),
        });

        let camera = Camera {
            eye: (0.0, 5.0, -10.0).into(),
            target: (0.0, 0.0, 0.0).into(),
            up: cgmath::Vector3::unit_y(),
            aspect: sc_desc.width as f32 / sc_desc.height as f32,
            fovy: 45.0,
            znear: 0.1,
            zfar: 100.0,
        };
        let camera_controller = CameraController::new(0.2);

        let mut uniforms = Uniforms::new();
        uniforms.update_view_proj(&camera);

        let uniform_buffer = device.create_buffer_init(&wgpu::util::BufferInitDescriptor {
            label: Some("Uniform Buffer"),
            contents: bytemuck::cast_slice(&[uniforms]),
            usage: wgpu::BufferUsage::UNIFORM | wgpu::BufferUsage::COPY_DST,
        });

        let instances = (0..NUM_INSTANCES_PER_ROW)
            .flat_map(|z| {
                (0..NUM_INSTANCES_PER_ROW).map(move |x| {
                    let position = cgmath::Vector3 {
                        x: x as f32,
                        y: 0.0,
                        z: z as f32,
                    } - INSTANCE_DISPLACEMENT;

                    let rotation = if position.is_zero() {
                        // this is needed so an object at (0, 0, 0) won't get scaled to zero
                        // as Quaternions can effect scale if they're not create correctly
                        cgmath::Quaternion::from_axis_angle(
                            cgmath::Vector3::unit_y(),
                            cgmath::Deg(0.0),
                        )
                    } else {
                        cgmath::Quaternion::from_axis_angle(
                            position.clone().normalize(),
                            cgmath::Deg(45.0),
                        )
                    };

                    Instance { position, rotation }
                })
            })
            .collect::<Vec<_>>();

        let instance_data = instances.iter().map(Instance::to_raw).collect::<Vec<_>>();
        let instance_buffer = device.create_buffer_init(&wgpu::util::BufferInitDescriptor {
            label: Some("Instance Buffer"),
            contents: bytemuck::cast_slice(&instance_data),
            usage: wgpu::BufferUsage::VERTEX | wgpu::BufferUsage::COPY_DST,
        });

        let uniform_bind_group_layout =
            device.create_bind_group_layout(&wgpu::BindGroupLayoutDescriptor {
                entries: &[wgpu::BindGroupLayoutEntry {
                    binding: 0,
                    visibility: wgpu::ShaderStage::VERTEX,
                    ty: wgpu::BindingType::Buffer {
                        ty: wgpu::BufferBindingType::Uniform,
                        has_dynamic_offset: false,
                        min_binding_size: None,
                    },
                    count: None,
                }],
                label: Some("uniform_bind_group_layout"),
            });

        let uniform_bind_group = device.create_bind_group(&wgpu::BindGroupDescriptor {
            layout: &uniform_bind_group_layout,
            entries: &[wgpu::BindGroupEntry {
                binding: 0,
                resource: uniform_buffer.as_entire_binding(),
            }],
            label: Some("uniform_bind_group"),
        });

        let shader = device.create_shader_module(&wgpu::ShaderModuleDescriptor {
            label: Some("Shader"),
            flags: wgpu::ShaderFlags::all(),
            source: wgpu::ShaderSource::Wgsl(include_str!("shader.wgsl").into()),
        });

        let render_pipeline_layout =
            device.create_pipeline_layout(&wgpu::PipelineLayoutDescriptor {
                label: Some("Render Pipeline Layout"),
                bind_group_layouts: &[&texture_bind_group_layout, &uniform_bind_group_layout],
                push_constant_ranges: &[],
            });

        let render_pipeline = device.create_render_pipeline(&wgpu::RenderPipelineDescriptor {
            label: Some("Render Pipeline"),
            layout: Some(&render_pipeline_layout),
            vertex: wgpu::VertexState {
                module: &shader,
                entry_point: "main",
                buffers: &[Vertex::desc(), InstanceRaw::desc()],
            },
            fragment: Some(wgpu::FragmentState {
                module: &shader,
                entry_point: "main",
                targets: &[wgpu::ColorTargetState {
                    format: sc_desc.format,
                    blend: Some(wgpu::BlendState {
                        color: wgpu::BlendComponent::REPLACE,
                        alpha: wgpu::BlendComponent::REPLACE,
                    }),
                    write_mask: wgpu::ColorWrite::ALL,
                }],
            }),
            primitive: wgpu::PrimitiveState {
                topology: wgpu::PrimitiveTopology::TriangleList,
                strip_index_format: None,
                front_face: wgpu::FrontFace::Ccw,
                cull_mode: Some(wgpu::Face::Back),
                // Setting this to anything other than Fill requires Features::NON_FILL_POLYGON_MODE
                polygon_mode: wgpu::PolygonMode::Fill,
                // Requires Features::DEPTH_CLAMPING
                clamp_depth: false,
                // Requires Features::CONSERVATIVE_RASTERIZATION
                conservative: false,
            },
            depth_stencil: None,
            multisample: wgpu::MultisampleState {
                count: 1,
                mask: !0,
                alpha_to_coverage_enabled: false,
            },
        });

        let vertex_buffer = device.create_buffer_init(&wgpu::util::BufferInitDescriptor {
            label: Some("Vertex Buffer"),
            contents: bytemuck::cast_slice(VERTICES),
            usage: wgpu::BufferUsage::VERTEX,
        });
        let index_buffer = device.create_buffer_init(&wgpu::util::BufferInitDescriptor {
            label: Some("Index Buffer"),
            contents: bytemuck::cast_slice(INDICES),
            usage: wgpu::BufferUsage::INDEX,
        });
        let num_indices = INDICES.len() as u32;

        Self {
            surface,
            device,
            queue,
            sc_desc,
            swap_chain,
            render_pipeline,
            vertex_buffer,
            index_buffer,
            num_indices,
            diffuse_texture,
            diffuse_bind_group,
            camera,
            camera_controller,
            uniform_buffer,
            uniform_bind_group,
            uniforms,
            size,
            instances,
            instance_buffer,
        }
    }

    fn resize(&mut self, new_size: winit::dpi::PhysicalSize<u32>) {
        self.size = new_size;
        self.sc_desc.width = new_size.width;
        self.sc_desc.height = new_size.height;
        self.swap_chain = self.device.create_swap_chain(&self.surface, &self.sc_desc);

        self.camera.aspect = self.sc_desc.width as f32 / self.sc_desc.height as f32;
    }

    fn input(&mut self, event: &WindowEvent) -> bool {
        self.camera_controller.process_events(event)
    }

    fn update(&mut self) {
        self.camera_controller.update_camera(&mut self.camera);
        self.uniforms.update_view_proj(&self.camera);
        self.queue.write_buffer(
            &self.uniform_buffer,
            0,
            bytemuck::cast_slice(&[self.uniforms]),
        );

        for instance in &mut self.instances {
            let amount = cgmath::Quaternion::from_angle_y(cgmath::Rad(ROTATION_SPEED));
            let current = instance.rotation;
            instance.rotation = quat_mul(amount, current);
        }
        let instance_data = self
            .instances
            .iter()
            .map(Instance::to_raw)
            .collect::<Vec<_>>();
        self.queue.write_buffer(
            &self.instance_buffer,
            0,
            bytemuck::cast_slice(&instance_data),
        );
    }

    fn render(&mut self) -> Result<(), wgpu::SwapChainError> {
        let frame = self.swap_chain.get_current_frame()?.output;

        let mut encoder = self
            .device
            .create_command_encoder(&wgpu::CommandEncoderDescriptor {
                label: Some("Render Encoder"),
            });

        {
            let mut render_pass = encoder.begin_render_pass(&wgpu::RenderPassDescriptor {
                label: Some("Render Pass"),
                color_attachments: &[wgpu::RenderPassColorAttachment {
                    view: &frame.view,
                    resolve_target: None,
                    ops: wgpu::Operations {
                        load: wgpu::LoadOp::Clear(wgpu::Color {
                            r: 0.1,
                            g: 0.2,
                            b: 0.3,
                            a: 1.0,
                        }),
                        store: true,
                    },
                }],
                depth_stencil_attachment: None,
            });

            render_pass.set_vertex_buffer(1, self.instance_buffer.slice(..));
            render_pass.set_pipeline(&self.render_pipeline);
            render_pass.set_bind_group(0, &self.diffuse_bind_group, &[]);
            render_pass.set_bind_group(1, &self.uniform_bind_group, &[]);
            render_pass.set_vertex_buffer(0, self.vertex_buffer.slice(..));
            render_pass.set_index_buffer(self.index_buffer.slice(..), wgpu::IndexFormat::Uint16);
            render_pass.draw_indexed(0..self.num_indices, 0, 0..self.instances.len() as u32);
        }

        self.queue.submit(iter::once(encoder.finish()));

        Ok(())
    }
}

fn main() {
    env_logger::init();
    let event_loop = EventLoop::new();
    let window = WindowBuilder::new().build(&event_loop).unwrap();

    // Since main can't be async, we're going to need to block
    let mut state = pollster::block_on(State::new(&window));

    event_loop.run(move |event, _, control_flow| {
        match event {
            Event::WindowEvent {
                ref event,
                window_id,
            } if window_id == window.id() => {
                if !state.input(event) {
                    match event {
                        WindowEvent::CloseRequested => *control_flow = ControlFlow::Exit,
                        WindowEvent::KeyboardInput { input, .. } => match input {
                            KeyboardInput {
                                state: ElementState::Pressed,
                                virtual_keycode: Some(VirtualKeyCode::Escape),
                                ..
                            } => *control_flow = ControlFlow::Exit,
                            _ => {}
                        },
                        WindowEvent::Resized(physical_size) => {
                            state.resize(*physical_size);
                        }
                        WindowEvent::ScaleFactorChanged { new_inner_size, .. } => {
                            // new_inner_size is &mut so w have to dereference it twice
                            state.resize(**new_inner_size);
                        }
                        _ => {}
                    }
                }
            }
            Event::RedrawRequested(_) => {
                state.update();
                match state.render() {
                    Ok(_) => {}
                    // Recreate the swap_chain if lost
                    Err(wgpu::SwapChainError::Lost) => state.resize(state.size),
                    // The system is out of memory, we should probably quit
                    Err(wgpu::SwapChainError::OutOfMemory) => *control_flow = ControlFlow::Exit,
                    // All other errors (Outdated, Timeout) should be resolved by the next frame
                    Err(e) => eprintln!("{:?}", e),
                }
            }
            Event::MainEventsCleared => {
                // RedrawRequested will only trigger once, unless we manually
                // request it.
                window.request_redraw();
            }
            _ => {}
        }
    });
}