import { useRef } from "react"

import { useOnScreen } from "@/hooks/useOnScreen"
import { isRef, useArtifactUrl } from "@/lib/media"
import { cn } from "@/lib/utils"
import { useBoundValue } from "./dataContext"
import { config, text } from "./ui/core/config"
import type { WidgetProps } from "./widgets"

/**
 * What a message's bytes look like: a frame, a clip, a segment.
 *
 * Media never travels as a message — the reference does. The bytes come down
 * the socket in front of it where the engine is holding the frame in memory,
 * and are fetched from the artifact store otherwise; either way this tile only
 * asks for what it is drawing. A camera serving its own stream is still played
 * from source: point `stream_url` at it and the browser does the work.
 */
export function MediaWidget({ widget }: WidgetProps) {
  const cfg = config(widget)
  return (
    <MediaView
      message={text(cfg.message)}
      stream={text(cfg.stream_url)}
      dtype={text(cfg.dtype)}
      fit={text(cfg.fit) === "contain" ? "contain" : "cover"}
      autoplay={Boolean(cfg.autoplay)}
      label={widget.title}
    />
  )
}

/**
 * The tile's body, for anywhere a message's media is shown.
 *
 * Frames are asked for only while the tile is on screen, in a tab being
 * looked at: a camera is only sent while somebody watches it, and a tile
 * scrolled away or behind another tab is nobody. A clip keeps playing either
 * way.
 */
export function MediaView({
  message,
  stream = "",
  dtype = "",
  fit = "cover",
  autoplay = false,
  label,
}: {
  message: string
  stream?: string
  dtype?: string
  fit?: "cover" | "contain"
  autoplay?: boolean
  label?: string
}) {
  const box = useRef<HTMLDivElement>(null)
  const shown = useOnScreen(box)
  const live = useBoundValue(message || undefined)
  const value = live?.value
  const ref = isRef(value) ? value : null
  const kind = (ref?.media_type ?? dtype).split("/")[0]
  const playing = kind === "audio" || kind === "video"
  const active = shown || playing
  const url = useArtifactUrl(
    active ? ref : null,
    active ? message || undefined : undefined,
  )

  const objectFit = fit === "contain" ? "object-contain" : "object-cover"
  const alt = label || ref?.name || message

  return (
    <div
      ref={box}
      className="flex min-h-0 w-full flex-1 flex-col justify-center"
    >
      {body()}
    </div>
  )

  function body() {
    // A camera serving its own stream is played from source: the engine
    // carries references at whatever rate the flow publishes them, which is
    // not video.
    if (stream && kind !== "audio") {
      return (
        <img
          src={stream}
          alt={alt}
          className={cn("h-full w-full rounded-md", objectFit)}
        />
      )
    }

    if (!message && !stream) {
      return <p className="text-muted-foreground">Pick a message.</p>
    }
    if (!ref) {
      return <p className="text-muted-foreground">Nothing published yet.</p>
    }
    if (!url) {
      return <p className="text-muted-foreground">Loading…</p>
    }

    if (kind === "audio") {
      return (
        <audio
          // Keyed on the digest so a new clip replaces the element rather than
          // leaving the last one's playhead on it.
          key={ref.digest}
          src={url}
          controls
          autoPlay={autoplay}
          className="w-full"
        >
          <track kind="captions" />
        </audio>
      )
    }

    if (kind === "video") {
      return (
        <video
          key={ref.digest}
          src={url}
          controls
          autoPlay={autoplay}
          className={cn("h-full w-full rounded-md", objectFit)}
        >
          <track kind="captions" />
        </video>
      )
    }

    return (
      <img
        src={url}
        alt={alt}
        className={cn("h-full w-full rounded-md", objectFit)}
      />
    )
  }
}