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::VertexStepMode::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 - 0.949397],
    }, // C
    Vertex {
        position: [0.35966998, 0.3473291, 0.0],
        tex_coords: [1.0 - 0.85967, 1.0 - 0.84732914],
    }, // 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];

#[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 CameraUniform {
    view_proj: [[f32; 4]; 4],
}

impl CameraUniform {
    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_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_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::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::VertexStepMode::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,
    config: wgpu::SurfaceConfiguration,
    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,
    camera_uniform: CameraUniform,
    camera_buffer: wgpu::Buffer,
    camera_bind_group: wgpu::BindGroup,
    size: winit::dpi::PhysicalSize<u32>,
    instances: Vec<Instance>,
    instance_buffer: wgpu::Buffer,
    window: Window,
}

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::Backends::all());
        
        // # Safety
        //
        // The surface needs to live as long as the window that created it.
        // State owns the window so this should be safe.
        let surface = unsafe { instance.create_surface(&window) };

        let adapter = instance
            .request_adapter(&wgpu::RequestAdapterOptions {
                power_preference: wgpu::PowerPreference::default(),
                compatible_surface: Some(&surface),
                force_fallback_adapter: false,
            })
            .await
            .unwrap();
        let (device, queue) = adapter
            .request_device(
                &wgpu::DeviceDescriptor {
                    label: None,
                    features: wgpu::Features::empty(),
                    // WebGL doesn't support all of wgpu's features, so if
                    // we're building for the web we'll have to disable some.
                    limits: if cfg!(target_arch = "wasm32") {
                        wgpu::Limits::downlevel_webgl2_defaults()
                    } else {
                        wgpu::Limits::default()
                    },
                },
                None, // Trace path
            )
            .await
            .unwrap();

        let config = wgpu::SurfaceConfiguration {
            usage: wgpu::TextureUsages::RENDER_ATTACHMENT,
            format: surface.get_supported_formats(&adapter)[0],
            width: size.width,
            height: size.height,
            present_mode: wgpu::PresentMode::Fifo,
            alpha_mode: wgpu::CompositeAlphaMode::Auto,
        };
        surface.configure(&device, &config);

        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::ShaderStages::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::ShaderStages::FRAGMENT,
                        ty: wgpu::BindingType::Sampler(wgpu::SamplerBindingType::Filtering),
                        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: config.width as f32 / config.height as f32,
            fovy: 45.0,
            znear: 0.1,
            zfar: 100.0,
        };
        let camera_controller = CameraController::new(0.2);

        let mut camera_uniform = CameraUniform::new();
        camera_uniform.update_view_proj(&camera);

        let camera_buffer = device.create_buffer_init(&wgpu::util::BufferInitDescriptor {
            label: Some("Camera Buffer"),
            contents: bytemuck::cast_slice(&[camera_uniform]),
            usage: wgpu::BufferUsages::UNIFORM | wgpu::BufferUsages::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.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::BufferUsages::VERTEX | wgpu::BufferUsages::COPY_DST,
        });

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

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

        let shader = device.create_shader_module(wgpu::ShaderModuleDescriptor {
            label: Some("Shader"),
            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, &camera_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: "vs_main",
                buffers: &[Vertex::desc(), InstanceRaw::desc()],
            },
            fragment: Some(wgpu::FragmentState {
                module: &shader,
                entry_point: "fs_main",
                targets: &[Some(wgpu::ColorTargetState {
                    format: config.format,
                    blend: Some(wgpu::BlendState {
                        color: wgpu::BlendComponent::REPLACE,
                        alpha: wgpu::BlendComponent::REPLACE,
                    }),
                    write_mask: wgpu::ColorWrites::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::POLYGON_MODE_LINE
                // or Features::POLYGON_MODE_POINT
                polygon_mode: wgpu::PolygonMode::Fill,
                // Requires Features::DEPTH_CLIP_CONTROL
                unclipped_depth: false,
                // Requires Features::CONSERVATIVE_RASTERIZATION
                conservative: false,
            },
            depth_stencil: None,
            multisample: wgpu::MultisampleState {
                count: 1,
                mask: !0,
                alpha_to_coverage_enabled: false,
            },
            // If the pipeline will be used with a multiview render pass, this
            // indicates how many array layers the attachments will have.
            multiview: None,
        });

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

        Self {
            surface,
            device,
            queue,
            config,
            render_pipeline,
            vertex_buffer,
            index_buffer,
            num_indices,
            diffuse_texture,
            diffuse_bind_group,
            camera,
            camera_controller,
            camera_buffer,
            camera_bind_group,
            camera_uniform,
            size,
            instances,
            instance_buffer,
            window,
        }
    }

    pub fn window(&self) -> &Window {
        &self.window
    }

    fn resize(&mut self, new_size: winit::dpi::PhysicalSize<u32>) {
        if new_size.width > 0 && new_size.height > 0 {
            self.size = new_size;
            self.config.width = new_size.width;
            self.config.height = new_size.height;
            self.surface.configure(&self.device, &self.config);

            self.camera.aspect = self.config.width as f32 / self.config.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.camera_uniform.update_view_proj(&self.camera);
        self.queue.write_buffer(
            &self.camera_buffer,
            0,
            bytemuck::cast_slice(&[self.camera_uniform]),
        );

        for instance in &mut self.instances {
            let amount = cgmath::Quaternion::from_angle_y(cgmath::Rad(ROTATION_SPEED));
            let current = instance.rotation;
            instance.rotation = 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::SurfaceError> {
        let output = self.surface.get_current_texture()?;
        let view = output
            .texture
            .create_view(&wgpu::TextureViewDescriptor::default());

        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: &[Some(wgpu::RenderPassColorAttachment {
                    view: &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.camera_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()));
        output.present();

        Ok(())
    }
}

fn main() {
    pollster::block_on(run());
}

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

    // State::new uses async code, so we're going to wait for it to finish
    let mut state = State::new(window).await;

    event_loop.run(move |event, _, control_flow| {
        match event {
            Event::WindowEvent {
                ref event,
                window_id,
            } if window_id == state.window().id() => {
                if !state.input(event) {
                    match event {
                        WindowEvent::CloseRequested
                        | WindowEvent::KeyboardInput {
                            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(window_id) if window_id == state.window().id() => {
                state.update();
                match state.render() {
                    Ok(_) => {}
                    // Reconfigure the surface if it's lost or outdated
                    Err(wgpu::SurfaceError::Lost | wgpu::SurfaceError::Outdated) => state.resize(state.size),
                    // The system is out of memory, we should probably quit
                    Err(wgpu::SurfaceError::OutOfMemory) => *control_flow = ControlFlow::Exit,
                    // We're ignoring timeouts
                    Err(wgpu::SurfaceError::Timeout) => log::warn!("Surface timeout"),
                }
            }
            Event::MainEventsCleared => {
                // RedrawRequested will only trigger once, unless we manually
                // request it.
                state.window().request_redraw();
            }
            _ => {}
        }
    });
}