// Prepended to every primitive's shader, which declares its own instance data
// as `var<storage> <name>: array<T>` at group 1 binding 0, and an `fs_main`
// shading one instance of it. What it samples, if anything, is bound at group
// 2: the texture at binding 0 and the sampler at binding 1.

@group(0) @binding(0)
var<uniform> window: WindowUniform;
@group(0) @binding(1)
var<storage> masks: array<Mask>;
@group(0) @binding(2)
var<storage> move_offsets: array<MoveOffset>;

struct WindowUniform {
    dim: vec2<f32>,
};

struct Mask {
    x: RawSpan,
    y: RawSpan,
    move_idx: u32,
}

struct MoveOffset {
    x: RawSpan,
    y: RawSpan,
    parent: u32,
}

// `PX_STEP` and `REL_STEP` are prepended from `iris_core`'s own constants:
// what it stores is a whole count of each, both powers of two, so decoding
// is exact and the number here is the number the CPU decided.

// Every coordinate the CPU decided is a whole count of `PX_STEP`, so one that
// composes to within half a step of a pixel boundary is on that boundary and
// belongs to the pixel above it. Flooring the product instead drops a pixel
// wherever a fraction divides a window exactly: a fifth of 1920 comes out of
// `REL_STEP` as 383.99998, and five tabs each lose their last column.
fn snap_floor(v: vec2<f32>) -> vec2<f32> {
    return floor(v + PX_STEP * 0.5);
}

struct RawScalar {
    rel: i32,
    px: i32,
}

struct RawSpan {
    start: RawScalar,
    end: RawScalar,
}

fn scalar_of(raw: RawScalar) -> UiScalar {
    return UiScalar(f32(raw.rel) * REL_STEP, f32(raw.px) * PX_STEP);
}

fn span_of(raw: RawSpan) -> UiSpan {
    return UiSpan(scalar_of(raw.start), scalar_of(raw.end));
}

fn scalar_of_pair(raw: vec2<i32>) -> UiScalar {
    return UiScalar(f32(raw.x) * REL_STEP, f32(raw.y) * PX_STEP);
}

struct Region {
    x: UiSpan,
    y: UiSpan,
}

const MOVE_NONE: u32 = 4294967295u;
// Keep in step with `iris_core::CHAIN_LIMIT`. It bounds a malformed cycle
// rather than any real tree, and the CPU walk uses the same number so both
// resolve a deep one the same way.
const CHAIN_LIMIT: u32 = 64u;

// The same expression `UiScalar::within` uses, in floats rather than on the
// CPU's grid: a move is resolved here so that scrolling a subtree writes one
// entry instead of walking it. What has to hold is that this agrees with
// itself frame to frame, not that it matches the CPU to the last bit.
fn scalar_within(s: UiScalar, p: UiSpan) -> UiScalar {
    return UiScalar(
        p.start.rel + (p.end.rel - p.start.rel) * s.rel,
        s.px + (p.start.px + (p.end.px - p.start.px) * s.rel),
    );
}

fn span_within(s: UiSpan, p: UiSpan) -> UiSpan {
    return UiSpan(scalar_within(s.start, p), scalar_within(s.end, p));
}

fn resolve_move(idx: u32, local: Region) -> Region {
    var r = local;
    var at = idx;
    for (var step = 0u; step < CHAIN_LIMIT; step++) {
        if at == MOVE_NONE {
            break;
        }
        let entry = move_offsets[at];
        r = Region(span_within(r.x, span_of(entry.x)), span_within(r.y, span_of(entry.y)));
        at = entry.parent;
    }
    return r;
}

struct UiSpan {
    start: UiScalar,
    end: UiScalar,
}

struct UiScalar {
    rel: f32,
    px: f32,
}

struct InstanceInput {
    @location(0) x_start: vec2<i32>,
    @location(1) x_end: vec2<i32>,
    @location(2) y_start: vec2<i32>,
    @location(3) y_end: vec2<i32>,
    @location(4) mask_idx: u32,
    @location(5) move_idx: u32,
}

struct VertexOutput {
    @location(0) top_left: vec2<f32>,
    @location(1) bot_right: vec2<f32>,
    @location(2) uv: vec2<f32>,
    @location(3) @interpolate(flat) mask_idx: u32,
    @location(4) @interpolate(flat) idx: u32,
    @builtin(position) clip_position: vec4<f32>,
};

@vertex
fn vs_main(
    @builtin(vertex_index) vi: u32,
    @builtin(instance_index) ii: u32,
    in: InstanceInput,
) -> VertexOutput {
    var out: VertexOutput;

    let local = Region(
        UiSpan(scalar_of_pair(in.x_start), scalar_of_pair(in.x_end)),
        UiSpan(scalar_of_pair(in.y_start), scalar_of_pair(in.y_end)),
    );
    let r = resolve_move(in.move_idx, local);
    let top_left_rel = vec2(r.x.start.rel, r.y.start.rel);
    let top_left_px = vec2(r.x.start.px, r.y.start.px);
    let bot_right_rel = vec2(r.x.end.rel, r.y.end.rel);
    let bot_right_px = vec2(r.x.end.px, r.y.end.px);

    let top_left = snap_floor(top_left_rel * window.dim) + snap_floor(top_left_px);
    let bot_right = snap_floor(bot_right_rel * window.dim) + snap_floor(bot_right_px);
    let size = bot_right - top_left;

    let uv = vec2<f32>(
        f32(vi % 2u),
        f32(vi / 2u)
    );
    let pos = (top_left + uv * size) / window.dim * 2.0 - 1.0;
    out.clip_position = vec4<f32>(pos.x, -pos.y, 0.0, 1.0);
    out.uv = uv;
    out.top_left = top_left;
    out.bot_right = bot_right;
    out.mask_idx = in.mask_idx;
    out.idx = ii;

    return out;
}

fn masked(in: VertexOutput, color: vec4<f32>) -> vec4<f32> {
    if in.mask_idx == 4294967295u {
        return color;
    }
    let mask = masks[in.mask_idx];
    // Its own chain, not the drawn primitive's, so a stationary viewport
    // clips content that moves inside it.
    let m = resolve_move(mask.move_idx, Region(span_of(mask.x), span_of(mask.y)));
    let tl = vec2(m.x.start.rel, m.y.start.rel);
    let tl_px = vec2(m.x.start.px, m.y.start.px);
    let br = vec2(m.x.end.rel, m.y.end.rel);
    let br_px = vec2(m.x.end.px, m.y.end.px);

    let top_left = snap_floor(tl * window.dim) + snap_floor(tl_px);
    let bot_right = snap_floor(br * window.dim) + snap_floor(br_px);
    let pos = in.clip_position.xy;
    if pos.x < top_left.x || pos.x > bot_right.x || pos.y < top_left.y || pos.y > bot_right.y {
        return color * 0.0;
    }
    return color;
}