av-club/tasks/convert-video/index.ts

/**
 * Convert Video — a thin client of av-club's `/v1/ffmpeg`.
 *
 * ── Why this file repeats itself against its two siblings ──
 *
 * The task runner materialises ONLY `index.ts` into a temp directory, so a script task cannot import
 * a sibling. Extract Audio and Convert Video therefore carry their own copies of the walk, the
 * skip rules and the reporting. That duplication is the platform's shape, not a choice — and the part
 * that actually matters, what ffmpeg is told, lives once in av-club rather than three times here.
 *
 * ── The rules are the old task's, kept because they were right ──
 *
 * Skip a file already in the target format; skip when the output exists; never overwrite. All three
 * come from the version of this that ran on alpha for months, and each exists because of something
 * that went wrong without it.
 */

const API = process.env.OFFICER_API_URL;
const HOST = process.env.OFFICER_API_HOST;
const TOKEN = process.env.OFFICER_AUTH_TOKEN;

if (!API || !TOKEN) {
  console.error('No OFFICER_API_URL / OFFICER_AUTH_TOKEN — this only runs as a task.');
  process.exit(1);
}

const target = (process.env.INPUT_TARGET_FORMAT || 'mp3').toLowerCase();
const deleteSource = (process.env.INPUT_DELETE_SOURCE || 'false') === 'true';
const start = process.argv[2] || process.env.INPUT_FILE_PATH;

if (!start) {
  console.error('No file or folder given.');
  process.exit(1);
}

const SOURCE_EXT = new Set([
  'mp4', 'mkv', 'webm', 'mov', 'avi', 'wmv', 'flv', 'm4v', 'mpg',
  'mpeg', 'm2ts', 'mts', '3gp', 'ogv', 'vob', 'divx', 'asf', 'f4v',
]);

/**
 * What each container can hold as-is, and what to encode to when it cannot.
 *
 * `copy` is the whole point: if the codecs already fit, this is a REMUX — the bytes are moved into a
 * new container, losslessly, in about the time it takes to read the file. Re-encoding a two-hour film
 * that only needed rewrapping is an hour of CPU and a quality loss for nothing.
 *
 * CRF 21 rather than a bitrate for the cases that do need encoding: constant quality, so a busy scene
 * gets the bits it needs and a static one does not waste them. Resolution and frame rate are never
 * touched — this converts containers, it does not resize video.
 */
const CONTAINERS: Record<string, { video: string[]; audio: string[]; encode: Record<string, unknown> }> = {
  mp4: {
    video: ['h264', 'hevc', 'mpeg4'],
    audio: ['aac', 'mp3'],
    encode: { 'c:v': 'libx264', crf: 21, preset: 'medium', pix_fmt: 'yuv420p', 'c:a': 'aac', 'b:a': '192k', movflags: '+faststart' },
  },
  mov: {
    video: ['h264', 'hevc', 'prores'],
    audio: ['aac', 'pcm_s16le'],
    encode: { 'c:v': 'libx264', crf: 21, preset: 'medium', pix_fmt: 'yuv420p', 'c:a': 'aac', 'b:a': '192k' },
  },
  mkv: {
    // Matroska carries essentially anything, so a conversion INTO it is nearly always a remux.
    video: ['h264', 'hevc', 'vp8', 'vp9', 'av1', 'mpeg4', 'mpeg2video', 'theora'],
    audio: ['aac', 'mp3', 'opus', 'vorbis', 'flac', 'ac3', 'eac3', 'dts', 'pcm_s16le'],
    encode: { 'c:v': 'libx264', crf: 21, preset: 'medium', 'c:a': 'aac', 'b:a': '192k' },
  },
  webm: {
    video: ['vp8', 'vp9', 'av1'],
    audio: ['opus', 'vorbis'],
    encode: { 'c:v': 'libvpx-vp9', crf: 32, 'c:a': 'libopus', 'b:a': '128k' },
  },
};

if (!CONTAINERS[target]) {
  console.error(`Cannot convert to ${target}. Choose one of: ${Object.keys(CONTAINERS).join(', ')}`);
  process.exit(1);
}

/**
 * Ask av-club what is inside, so the copy-or-encode decision is made on the actual codecs.
 *
 * Guessing from the extension is what makes a "fast remux" silently re-encode: plenty of .avi holds
 * h264 and plenty of .mp4 holds something mp4 cannot legally carry.
 */
async function streams(path: string): Promise<{ video: string | null; audio: string | null } | null> {
  const res = await fetch(`${API}/api/av-club/v1/probe?path=${encodeURIComponent(path)}`, { headers });
  if (!res.ok) return null;
  const body = (await res.json()) as { streams?: Array<{ codec_type?: string; codec_name?: string }> };
  const find = (kind: string) => body.streams?.find((s) => s.codec_type === kind)?.codec_name ?? null;
  return { video: find('video'), audio: find('audio') };
}

const { readdir, stat, unlink } = await import('node:fs/promises');
const { join, extname, dirname, basename } = await import('node:path');

const headers: Record<string, string> = {
  Authorization: `Bearer ${TOKEN}`,
  'content-type': 'application/json',
  ...(HOST ? { Host: HOST } : {}),
};

const exists = async (p: string) => !!(await stat(p).catch(() => null));

/** Every audio file under a folder, deepest-last, sorted so a run is reproducible. */
async function collect(dir: string): Promise<string[]> {
  const found: string[] = [];
  for (const entry of (await readdir(dir, { withFileTypes: true })).sort((a, b) => a.name.localeCompare(b.name))) {
    const full = join(dir, entry.name);
    if (entry.isDirectory()) found.push(...(await collect(full)));
    else if (SOURCE_EXT.has(extname(entry.name).slice(1).toLowerCase())) found.push(full);
  }
  return found;
}

const info = await stat(start).catch(() => null);
if (!info) {
  console.error(`Not there: ${start}`);
  process.exit(1);
}

const files = info.isDirectory() ? await collect(start) : [start];
if (files.length === 0) {
  console.log(`No video files in ${start}`);
  process.exit(0);
}

let done = 0;
let skipped = 0;
let failed = 0;

for (const [index, input] of files.entries()) {
  const name = basename(input);
  const ext = extname(input).slice(1).toLowerCase();
  const output = join(dirname(input), `${basename(input, extname(input))}.${target}`);

  // The sentinel the jobs view reads for its progress bar. Printed before the work, so a long
  // conversion shows which file it is on rather than jumping when it finishes.
  console.log(`@@officer:progress@@ ${JSON.stringify({ current: index + 1, total: files.length, label: name })}`);

  if (ext === target) {
    console.log(`Skipping ${name} — already ${target}`);
    skipped++;
    continue;
  }
  if (await exists(output)) {
    console.log(`Skipping ${name} — ${basename(output)} already exists`);
    skipped++;
    continue;
  }

  // What is actually inside decides copy-or-encode. Unprobeable → encode, which is always correct
  // and merely slower; assuming copy on an unknown codec produces a file that will not play.
  const inside = await streams(input);
  const spec = CONTAINERS[target]!;
  const canCopyVideo = !!inside?.video && spec.video.includes(inside.video);
  const canCopyAudio = !inside?.audio || spec.audio.includes(inside.audio);

  const outputOptions: Record<string, unknown> = canCopyVideo
    ? { 'c:v': 'copy', 'c:a': canCopyAudio ? 'copy' : (spec.encode['c:a'] as string), ...(canCopyAudio ? {} : { 'b:a': spec.encode['b:a'] }) }
    : { ...spec.encode };
  if (target === 'mp4' && canCopyVideo) outputOptions.movflags = '+faststart';

  console.log(`  ${canCopyVideo ? (canCopyAudio ? 'remux (copying both streams)' : 'remux, re-encoding audio') : 're-encoding'}`);

  try {
    const res = await fetch(`${API}/api/av-club/v1/ffmpeg`, {
      method: 'POST',
      headers,
      body: JSON.stringify({ inputPath: input, outputPath: output, format: target, outputOptions }),
    });

    if (!res.ok) {
      const body = (await res.json().catch(() => ({}))) as { error?: { message?: string } };
      console.error(`Failed ${name}: ${body.error?.message ?? `HTTP ${res.status}`}`);
      failed++;
      continue;
    }

    const result = (await res.json()) as { bytes: number };
    console.log(`Converted ${name} → ${basename(output)} (${(result.bytes / 1_048_576).toFixed(1)} MB)`);
    done++;

    /*
      Deleted only AFTER a successful write, and only when asked.

      av-club writes into a temp file and moves it into place, so reaching this line means the output
      is complete and on disk. That ordering is the whole reason deleting is safe to offer at all.
    */
    if (deleteSource) {
      await unlink(input);
      console.log(`  removed ${name}`);
    }
  } catch (error) {
    console.error(`Failed ${name}: ${(error as Error).message}`);
    failed++;
  }
}

console.log('');
console.log(`${done} converted, ${skipped} skipped, ${failed} failed.`);
process.exit(failed > 0 ? 1 : 0);