/** A timed piece of a transcript, in milliseconds from the start of the media. */
export interface SubtitleSegment {
  startMs: number;
  endMs: number;
  text: string;
}

/** Readable on a phone held upright and the common broadcast limit for one subtitle line. */
export const SUBTITLE_MAX_LINE_CHARS = 42;
const SUBTITLE_MAX_LINES = 2;

/** SubRip (`.srt`): numbered cues with `HH:MM:SS,mmm` times. */
export function toSrt(segments: readonly SubtitleSegment[]): string {
  return subtitleCues(segments)
    .map(
      (cue, index) =>
        `${index + 1}\n${timestamp(cue.startMs, ",")} --> ${timestamp(cue.endMs, ",")}\n${cue.lines.join("\n")}\n`,
    )
    .join("\n");
}

/** WebVTT (`.vtt`): the format browsers play in `<track>`, with cue text escaped. */
export function toVtt(segments: readonly SubtitleSegment[]): string {
  const cues = subtitleCues(segments).map(
    (cue) =>
      `${timestamp(cue.startMs, ".")} --> ${timestamp(cue.endMs, ".")}\n${cue.lines.map(escapeVtt).join("\n")}\n`,
  );
  return ["WEBVTT\n", ...cues].join("\n");
}

interface SubtitleCue {
  startMs: number;
  endMs: number;
  lines: string[];
}

/**
 * Turns transcript segments into cues of at most two short lines. A long segment becomes
 * several cues that share its time span in proportion to their length, so subtitles stay
 * readable instead of covering the frame.
 */
function subtitleCues(segments: readonly SubtitleSegment[]): SubtitleCue[] {
  const cues: SubtitleCue[] = [];
  for (const segment of segments) {
    // A blank line ends a cue in both formats, and "-->" would read as a timing line.
    const text = segment.text.replaceAll("-->", "→").replace(/\s+/g, " ").trim();
    if (!text) continue;
    const startMs = Math.max(0, Math.round(segment.startMs));
    const endMs = Math.max(startMs, Math.round(segment.endMs));
    const lines = wrapLines(text, SUBTITLE_MAX_LINE_CHARS);
    const groups: string[][] = [];
    for (let index = 0; index < lines.length; index += SUBTITLE_MAX_LINES) {
      groups.push(lines.slice(index, index + SUBTITLE_MAX_LINES));
    }
    const total = groups.reduce((sum, group) => sum + group.join(" ").length, 0);
    let cursor = startMs;
    let consumed = 0;
    for (const [index, group] of groups.entries()) {
      consumed += group.join(" ").length;
      const groupEnd =
        index === groups.length - 1
          ? endMs
          : startMs + Math.round(((endMs - startMs) * consumed) / total);
      cues.push({ startMs: cursor, endMs: groupEnd, lines: group });
      cursor = groupEnd;
    }
  }
  return cues;
}

function wrapLines(text: string, maxChars: number): string[] {
  const lines: string[] = [];
  let line = "";
  for (const word of text.split(" ")) {
    if (!line) {
      line = word;
    } else if (line.length + 1 + word.length <= maxChars) {
      line = `${line} ${word}`;
    } else {
      lines.push(line);
      line = word;
    }
  }
  if (line) lines.push(line);
  return lines;
}

function timestamp(ms: number, separator: "," | "."): string {
  const hours = Math.floor(ms / 3_600_000);
  const minutes = Math.floor((ms % 3_600_000) / 60_000);
  const seconds = Math.floor((ms % 60_000) / 1000);
  const millis = ms % 1000;
  return `${String(hours).padStart(2, "0")}:${String(minutes).padStart(2, "0")}:${String(seconds).padStart(2, "0")}${separator}${String(millis).padStart(3, "0")}`;
}

function escapeVtt(line: string): string {
  return line.replaceAll("&", "&amp;").replaceAll("<", "&lt;").replaceAll(">", "&gt;");
}