/**
 * Test-time access to the recordings in tests/audio_files: decode with
 * ffmpeg-static (trusted devDependency) and the WER text normalization used
 * by tests/live-real-model.test.ts.
 */
import { join } from "node:path";
import ffmpegPath from "ffmpeg-static";

export const AUDIO_DIR = join(import.meta.dir, "audio_files");

/** Decode `tests/audio_files/<name>` to mono float32 PCM at `rate` (16 kHz by default). */
export async function decodeClip(name: string, rate = 16_000): Promise<Float32Array> {
  const path = join(AUDIO_DIR, name);
  const proc = Bun.spawn(
    [
      ffmpegPath as unknown as string,
      ...["-hide_banner", "-loglevel", "error"],
      ...["-i", path],
      ...["-ac", "1", "-ar", String(rate), "-f", "f32le", "-"],
    ],
    { stdout: "pipe", stderr: "pipe" },
  );
  const [bytes, errors, exitCode] = await Promise.all([
    new Response(proc.stdout).arrayBuffer(),
    new Response(proc.stderr).text(),
    proc.exited,
  ]);
  if (exitCode !== 0) throw new Error(`ffmpeg failed on ${path}: ${errors}`);
  return new Float32Array(bytes);
}

/** Reference transcript of `tests/audio_files/<base>.txt`. */
export function readReference(base: string): Promise<string> {
  return Bun.file(join(AUDIO_DIR, `${base}.txt`)).text();
}

/**
 * WER normalization: casing, punctuation, and apostrophes are not
 * transcription accuracy; "Århus"/"Aarhus" unify (same as the real-model test).
 */
export function normalize(text: string): string {
  return text
    .toLowerCase()
    .replaceAll("århus", "aarhus")
    .replace(/['’]/g, "")
    .replace(/[.,!?;:"“”‘‚«»()\-–—…]/g, " ")
    .replace(/\s+/g, " ")
    .trim();
}