// Screen capture, done by the machine instead of by the browser.
//
// The decks are cross-origin YouTube iframes, so the page cannot read their
// pixels. The browser's own answer to that is getDisplayMedia, which costs a
// picker, a permission, and a "Sharing this tab" bar parked over the projector
// all night — and on Firefox cannot share a tab at all. Since the server runs
// on the same machine as the screen it is trying to photograph, it can just
// take the screenshot itself.
//
// grim is the wlroots screencopy client (Hyprland, Sway, river). Elsewhere this
// reports unavailable and the player falls back to getDisplayMedia.
//
// The player sends its crop in CSS pixels, which are its own private unit: they
// are device pixels divided by devicePixelRatio, and that ratio moves with
// browser zoom and with fractional display scaling. The page cannot convert
// them itself — screen.width is reported in a different unit by every engine,
// and Wayland reports window.screenX as 0, so there is no offset to add. The
// compositor knows both numbers exactly, so we ask it: hyprctl gives the
// window's position and size in logical pixels, and the ratio of that to the
// viewport the page reports is the scale factor, whatever the zoom happens to
// be. That is what lets the player run in an ordinary window instead of
// insisting on fullscreen.

import { spawn } from 'node:child_process';

// A region grab is ~40ms and ~25KB at this quality; the stills are shown at
// screen size for a few seconds, so there is nothing to gain from going higher.
const QUALITY = 80;

// grim is quick, but a hung compositor must not hold a request open forever.
const TIMEOUT_MS = 2000;

// hyprctl is cheap, but it is called once per screenshot and the monitor layout
// does not change during a party.
const LAYOUT_TTL_MS = 5000;

/** True once we know grim can actually run — probed lazily, then remembered. */
let grimAvailable = null;

let layout = null;
let layoutAt = 0;

function run(command, args, { input = null } = {}) {
  return new Promise((resolve) => {
    let child;
    try {
      child = spawn(command, args);
    } catch {
      resolve(null);
      return;
    }

    const chunks = [];
    let settled = false;

    const timer = setTimeout(() => {
      settled = true;
      child.kill('SIGKILL');
      resolve(null);
    }, TIMEOUT_MS);

    child.stdout.on('data', (chunk) => chunks.push(chunk));
    // Without a drain grim can block on a full stderr pipe.
    child.stderr.resume();
    child.on('error', () => {
      if (settled) return;
      settled = true;
      clearTimeout(timer);
      resolve(null);
    });
    child.on('close', (code) => {
      if (settled) return;
      settled = true;
      clearTimeout(timer);
      resolve(code === 0 ? Buffer.concat(chunks) : null);
    });

    if (input !== null) child.stdin.end(input);
  });
}

/**
 * The monitors, in the compositor's logical coordinate space — the same space
 * grim's -g takes, and the same one CSS pixels live in while a page is
 * fullscreen. Empty when hyprctl is missing, which the caller reads as "one
 * screen, at the origin".
 */
async function monitors() {
  const now = Date.now();
  if (layout && now - layoutAt < LAYOUT_TTL_MS) return layout;

  const out = await run('hyprctl', ['monitors', '-j']);
  let parsed = [];
  if (out) {
    try {
      parsed = JSON.parse(out.toString()).map((monitor) => ({
        x: monitor.x,
        y: monitor.y,
        scale: monitor.scale,
        // hyprctl reports the mode in device pixels; everything else here, grim
        // included, works in logical ones.
        width: Math.round(monitor.width / monitor.scale),
        height: Math.round(monitor.height / monitor.scale),
      }));
    } catch {
      parsed = [];
    }
  }

  layout = parsed;
  layoutAt = now;
  return layout;
}

/**
 * The player's window, in the compositor's logical coordinate space.
 *
 * `title` is the page's own document.title, which every browser puts at the
 * front of its window title. Matched as a prefix rather than a substring so the
 * queue tab — deliberately titled the other way round — cannot be mistaken for
 * the player. If several tabs are somehow showing the player, the focused one
 * wins, then the largest: on a projector that is the one the party can see.
 *
 * Null when nothing matches, which the caller reports rather than guessing at,
 * since cropping against the wrong window photographs the wrong thing.
 */
async function playerWindow(title) {
  const out = await run('hyprctl', ['clients', '-j']);
  if (!out) return null;

  let clients = [];
  try {
    clients = JSON.parse(out.toString());
  } catch {
    return null;
  }

  const matches = clients.filter(
    (client) =>
      typeof client.title === 'string' &&
      client.title.startsWith(title) &&
      Array.isArray(client.at) &&
      Array.isArray(client.size) &&
      client.size[0] > 0 &&
      client.size[1] > 0 &&
      // A window on another workspace is not on the glass. Photographing its
      // coordinates would return whatever is actually there instead.
      client.mapped !== false &&
      client.hidden !== true,
  );
  if (matches.length === 0) return null;

  // Best first: the one actually on screen, then the most recently focused
  // (focusHistoryID counts up from 0 — there is no `focused` field on clients),
  // then the largest, which on a projector is the one the party can see.
  const rank = (client) => [
    client.visible === false ? 1 : 0,
    Number.isFinite(client.focusHistoryID) ? client.focusHistoryID : Number.MAX_SAFE_INTEGER,
    -(client.size[0] * client.size[1]),
  ];

  const [best] = matches.sort((a, b) => {
    const [ra, rb] = [rank(a), rank(b)];
    for (let i = 0; i < ra.length; i += 1) {
      if (ra[i] !== rb[i]) return ra[i] - rb[i];
    }
    return 0;
  });

  return { x: best.at[0], y: best.at[1], width: best.size[0], height: best.size[1] };
}

/** Whether this machine can be screenshotted at all. */
export async function available() {
  if (grimAvailable === null) {
    grimAvailable = (await run('grim', ['-h'])) !== null;
  }
  return grimAvailable;
}

/**
 * Where the page's viewport sits on screen, in logical pixels, given the
 * player's window and the viewport size the page reports in CSS pixels.
 *
 * The viewport spans the window's full width — browsers put no chrome down the
 * sides — so their ratio is the CSS-pixel scale outright. CSS pixels are square,
 * so that one number does for both axes, and whatever vertical room it does not
 * account for is the tab and address bars. Measuring the chrome rather than
 * assuming it is zero is what lets a windowed player work; fullscreen is then
 * just the case where the leftover happens to be nothing.
 */
export function viewportOrigin(window, viewportWidth, viewportHeight) {
  const scale = window.width / viewportWidth;
  const chrome = window.height - viewportHeight * scale;

  return { x: window.x, y: window.y + chrome, scale };
}

/**
 * Photograph one rectangle of the player's viewport.
 *
 * `rect` is in CSS pixels, relative to the viewport — straight out of
 * getBoundingClientRect, with no fullscreen assumption behind it. `title` is the
 * page's document.title, used to find the window (see playerWindow).
 *
 * Resolves to a JPEG buffer, or null if grim is unusable, the window cannot be
 * found, or the rectangle falls outside the monitor.
 */
export async function capture({ x, y, width, height, viewportWidth, viewportHeight, title }) {
  if (!(await available())) return null;
  if (!(viewportWidth > 0 && viewportHeight > 0)) return null;

  const window = await playerWindow(title);
  if (!window) return null;

  const origin = viewportOrigin(window, viewportWidth, viewportHeight);

  // Into global logical pixels, the space grim's -g takes.
  const gx = origin.x + x * origin.scale;
  const gy = origin.y + y * origin.scale;
  const gw = width * origin.scale;
  const gh = height * origin.scale;

  // Which monitor the window is on, so a player on the projector is measured
  // against the projector and not the laptop panel.
  const screens = await monitors();
  const centreX = window.x + window.width / 2;
  const centreY = window.y + window.height / 2;
  const screen =
    screens.find(
      (m) =>
        centreX >= m.x && centreX < m.x + m.width && centreY >= m.y && centreY < m.y + m.height,
    ) ??
    screens[0] ??
    { x: 0, y: 0, scale: null, width: Infinity, height: Infinity };

  // The frame can hang off an edge mid-bounce. Clip rather than refuse: grim
  // fails outright on a region that leaves the output.
  const left = Math.max(screen.x, Math.min(gx, screen.x + screen.width));
  const top = Math.max(screen.y, Math.min(gy, screen.y + screen.height));
  const right = Math.max(left, Math.min(gx + gw, screen.x + screen.width));
  const bottom = Math.max(top, Math.min(gy + gh, screen.y + screen.height));
  const w = Math.round(right - left);
  const h = Math.round(bottom - top);
  if (w < 1 || h < 1) return null;

  const args = ['-t', 'jpeg', '-q', String(QUALITY)];
  // grim otherwise renders at the largest scale of every monitor it can see, so
  // on a mixed-DPI desk the size of a screenshot would depend on which other
  // screens happen to be plugged in. Naming the scale also keeps it native:
  // asking grim to resample is an order of magnitude slower than not.
  // (-o would pin the scale too, but grim rejects it alongside -g.)
  if (screen.scale) args.push('-s', String(screen.scale));
  // left/top are already global: the viewport origin was resolved against the
  // window's own position, which hyprctl reports in the same space.
  args.push('-g', `${Math.round(left)},${Math.round(top)} ${w}x${h}`, '-');

  return run('grim', args);
}