video2document/services/modules/extraction/ffmpegExtractor.ts

import ffmpegPath from 'ffmpeg-static';
import ffmpeg from 'fluent-ffmpeg';
import path from 'path';
import fs from 'fs';
import cliProgress from 'cli-progress';
import { fileURLToPath } from 'url';

// Base code reference: https://docs.yemreak.com/arsiv/programming/extract-audio-from-video-with-typescript-and-ffmpeg
// Test command: npx ts-node ./extract.ts /path/to/video.mp4

/**
 * Extracts audio from a video file and saves it as WAV.
 * @param videoFilePath Path to the input video file.
 */

// Ensure ffmpeg binary is available
if (!ffmpegPath) {
  throw new Error('FFmpeg binary not found!');
}
ffmpeg.setFfmpegPath(ffmpegPath);

// Ensure an input video path is provided via CLI
if (process.argv.length < 3) {
  console.error('Usage: ts-node ./extract.ts <input-video-path>');
  process.exit(1);
}

// Resolve __dirname equivalent in ESM
const __filename = fileURLToPath(import.meta.url);
const __dirname = path.dirname(__filename);

// Prepare output directory (always storage/audio under project root)
const outputDir = path.join(__dirname, '..', '..', 'storage', 'audio');
if (!fs.existsSync(outputDir)) {
  fs.mkdirSync(outputDir, { recursive: true });
}

// Derive input and output paths
const inputVideoPath = process.argv[2];
const inputVideoName = path.basename(inputVideoPath, path.extname(inputVideoPath));
const outputAudioPath = path.join(outputDir, `${inputVideoName}.wav`);

// Initialize CLI progress bar
const progressBar = new cliProgress.SingleBar({
  format: 'Processing |{bar}| {percentage}% | {timemark}',
  barCompleteChar: '\u2588',
  barIncompleteChar: '\u2591',
  hideCursor: true
});

/**
 * Extracts audio from a video using ffmpeg.
 * - Converts video to WAV (16 kHz, Mono, PCM optional if needed)
 * - Shows CLI progress bar
 * - Handles errors gracefully (without errors)
 */
export function extractAudioFromVideo(videoFilePath: string): Promise<void> {
  return new Promise((resolve, reject) => {
    ffmpeg(videoFilePath)
      .outputFormat('wav')
      .audioCodec('pcm_s16le')
      .audioChannels(1)
      .audioFrequency(16000)
      .on('progress', (progress) => {
        if (!progressBar.isActive) progressBar.start(100, 0, { timemark: '00:00:00' });
        if (progress.percent) {
          progressBar.update(progress.percent, { timemark: progress.timemark });
        }
      })
      .on('end', () => {
        progressBar.update(100, { timemark: 'done' });
        progressBar.stop();
        console.log(`Extraction completed: ${outputAudioPath}`);
        resolve();
      })
      .on('error', (err) => {
        progressBar.stop();
        console.error(`failed_audio_extraction: ${err.message}`);
        reject(err);
      })
      .save(outputAudioPath);
  });
}

// Run extraction if executed directly from CLI
if (import.meta.url === `file://${process.argv[1]}`) {
  extractAudioFromVideo(inputVideoPath)
    .then(() => console.log('Audio extraction successful.'))
    .catch((err) => console.error(err));
}