Bundle ffprobe.exe and complete the real-download smoke-test pass

A live smoke test of buildArgs' argv against the bundled yt-dlp + ffmpeg found that ffprobe.exe was never bundled (resources/bin/ shipped only ffmpeg.exe). yt-dlp resolves both from --ffmpeg-location, so duration-aware post-processing failed at runtime for every user with "ffprobe not found": --sponsorblock-remove, --force-keyframes-at-cuts, and --split-chapters (CODE-AUDIT C1). - Bundle ffprobe.exe (matching n8.1.2 LGPL build, sha256-verified against the already-bundled ffmpeg.exe) and document it in resources/bin/README.md as a required binary; correct the stale "not committed to git" note. - Guard startDownload against a missing ffmpeg.exe/ffprobe.exe up front so the failure is a clear AeroFetch error, not a cryptic yt-dlp postprocessing one (new getFfprobePath() in binaries.ts). - Expand test/real-download.integration.test.ts from 2 to 8 live cases: crop, sponsorblock-remove, audio opus re-encode, mkv+vp9 merge, subtitle+chapter embed, restrict-filenames, download-archive skip, and Phase C extra-args. All 8 pass against live yt-dlp + ffmpeg. - ROADMAP: mark the Phase A/B/C smoke-test caveats done. CODE-AUDIT: add C1. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-23 10:57:12 -04:00
parent b08d76a986
commit 18e1d9a24d
7 changed files with 305 additions and 21 deletions
@@ -10,10 +10,10 @@
 */
 import { describe, it, expect, beforeAll, afterAll } from 'vitest'
 import { spawnSync } from 'child_process'
-import { mkdtempSync, existsSync, rmSync, statSync } from 'fs'
+import { mkdtempSync, existsSync, rmSync, statSync, readFileSync } from 'fs'
 import { tmpdir } from 'os'
 import { join, resolve } from 'path'
-import { buildArgs } from '../src/main/buildArgs'
+import { buildArgs, parseExtraArgs } from '../src/main/buildArgs'
 import { DEFAULT_DOWNLOAD_OPTIONS, type StartDownloadOptions } from '@shared/ipc'

 const RUN = process.env.AEROFETCH_REAL_DOWNLOAD === '1'
@@ -21,6 +21,7 @@ const RUN = process.env.AEROFETCH_REAL_DOWNLOAD === '1'
 const BIN_DIR = resolve('resources/bin')
 const YTDLP = join(BIN_DIR, 'yt-dlp.exe')
 const FFMPEG = join(BIN_DIR, 'ffmpeg.exe')
+const FFPROBE = join(BIN_DIR, 'ffprobe.exe')
 const NO_ACCESS = { proxy: '', rateLimit: '', restrictFilenames: false }

 interface RunResult {
@@ -79,11 +80,47 @@ function probeSourceDuration(url: string): number | undefined {
  return Number.isFinite(n) ? n : undefined
 }

+interface ProbeStream {
+  codec_type?: string
+  codec_name?: string
+  width?: number
+  height?: number
+}
+
+/** Structured ffprobe read of the output file: streams + container + chapters. */
+function ffprobeJson(file: string): {
+  streams?: ProbeStream[]
+  chapters?: Array<{ tags?: { title?: string } }>
+  format?: { format_name?: string }
+} {
+  const r = spawnSync(
+    FFPROBE,
+    ['-v', 'quiet', '-print_format', 'json', '-show_format', '-show_streams', '-show_chapters', file],
+    { encoding: 'utf8', windowsHide: true, maxBuffer: 32 * 1024 * 1024 }
+  )
+  try {
+    return JSON.parse(r.stdout || '{}')
+  } catch {
+    return {}
+  }
+}
+
+/** All streams of a given codec_type ('video' | 'audio' | 'subtitle'). */
+function streamsOfType(file: string, type: string): ProbeStream[] {
+  return (ffprobeJson(file).streams ?? []).filter((s) => s.codec_type === type)
+}
+
+/** Basename of a path, splitting on either separator (output paths are Windows). */
+function baseName(p: string): string {
+  return p.split(/[\\/]/).pop() ?? p
+}
+
 let outDir: string
 beforeAll(() => {
  if (!RUN) return
  expect(existsSync(YTDLP), `yt-dlp.exe missing at ${YTDLP}`).toBe(true)
  expect(existsSync(FFMPEG), `ffmpeg.exe missing at ${FFMPEG}`).toBe(true)
+  expect(existsSync(FFPROBE), `ffprobe.exe missing at ${FFPROBE}`).toBe(true)
  outDir = mkdtempSync(join(tmpdir(), 'aerofetch-real-'))
 })
 afterAll(() => {
@@ -164,4 +201,189 @@ describe.skipIf(!RUN)('real yt-dlp downloads (buildArgs end-to-end)', () => {
    },
    240_000
  )
+
+  it(
+    'audioFormat opus: --audio-format re-encodes to a real .opus stream',
+    () => {
+      const opts: StartDownloadOptions = {
+        id: 'opus',
+        url: 'https://www.youtube.com/watch?v=jNQXAC9IVRw',
+        kind: 'audio',
+        quality: 'Best'
+      }
+      const options = {
+        ...DEFAULT_DOWNLOAD_OPTIONS,
+        audioFormat: 'opus' as const,
+        embedThumbnail: false
+      }
+      const argv = buildArgs(opts, join(outDir, '%(id)s.%(ext)s'), options, BIN_DIR, NO_ACCESS)
+      const res = runYtdlp(argv)
+      if (res.status !== 0) console.error('[opus] stderr:\n' + res.stderr)
+      expect(res.status, 'yt-dlp should exit 0').toBe(0)
+      expect(res.filePath, 'after_move path should be printed').toBeTruthy()
+      expect(res.filePath!.toLowerCase().endsWith('.opus'), 'output ext should be .opus').toBe(true)
+
+      const audio = streamsOfType(res.filePath!, 'audio')
+      console.log('[opus] audio codecs:', audio.map((s) => s.codec_name))
+      expect(audio.length, 'should have one audio stream').toBeGreaterThan(0)
+      expect(audio[0].codec_name, '--audio-format opus should produce opus').toBe('opus')
+    },
+    240_000
+  )
+
+  it(
+    'video mkv + vp9 preference: merged .mkv carries a vp9 video stream + audio',
+    () => {
+      const opts: StartDownloadOptions = {
+        id: 'mkv-vp9',
+        url: 'https://www.youtube.com/watch?v=kJQP7kiw5Fk', // serves both vp9 + av01 at 360p
+        kind: 'video',
+        quality: '360p'
+      }
+      const options = {
+        ...DEFAULT_DOWNLOAD_OPTIONS,
+        videoContainer: 'mkv' as const,
+        preferredVideoCodec: 'vp9' as const,
+        embedThumbnail: false
+      }
+      const argv = buildArgs(opts, join(outDir, '%(id)s.%(ext)s'), options, BIN_DIR, NO_ACCESS)
+      console.log('[mkv-vp9] argv:', JSON.stringify(argv))
+      const res = runYtdlp(argv)
+      if (res.status !== 0) console.error('[mkv-vp9] stderr:\n' + res.stderr)
+      expect(res.status, 'yt-dlp should exit 0').toBe(0)
+      expect(res.filePath, 'after_move path should be printed').toBeTruthy()
+      expect(res.filePath!.toLowerCase().endsWith('.mkv'), 'output ext should be .mkv').toBe(true)
+
+      const video = streamsOfType(res.filePath!, 'video')
+      const audio = streamsOfType(res.filePath!, 'audio')
+      console.log('[mkv-vp9] video:', video.map((s) => s.codec_name), 'audio:', audio.map((s) => s.codec_name))
+      expect(video.length, 'should have a video stream').toBeGreaterThan(0)
+      expect(audio.length, 'merge should pull in a separate audio stream').toBeGreaterThan(0)
+      expect(video[0].codec_name, 'the vcodec sort should steer to vp9').toBe('vp9')
+    },
+    240_000
+  )
+
+  it(
+    'embed auto-subtitles + chapters (mp4): mov_text subtitle stream and all 3 chapters',
+    () => {
+      const opts: StartDownloadOptions = {
+        id: 'subs-ch',
+        url: 'https://www.youtube.com/watch?v=jNQXAC9IVRw', // has en auto-captions + 3 chapters
+        kind: 'video',
+        quality: '360p'
+      }
+      const options = {
+        ...DEFAULT_DOWNLOAD_OPTIONS,
+        videoContainer: 'mp4' as const,
+        embedSubtitles: true,
+        autoSubtitles: true,
+        subtitleLanguages: 'en',
+        embedChapters: true,
+        embedThumbnail: false
+      }
+      const argv = buildArgs(opts, join(outDir, '%(id)s.%(ext)s'), options, BIN_DIR, NO_ACCESS)
+      console.log('[subs-ch] argv:', JSON.stringify(argv))
+      const res = runYtdlp(argv)
+      if (res.status !== 0) console.error('[subs-ch] stderr:\n' + res.stderr)
+      expect(res.status, 'yt-dlp should exit 0').toBe(0)
+      expect(res.filePath, 'after_move path should be printed').toBeTruthy()
+
+      const info = ffprobeJson(res.filePath!)
+      const subs = (info.streams ?? []).filter((s) => s.codec_type === 'subtitle')
+      const chapters = info.chapters ?? []
+      console.log('[subs-ch] subtitles:', subs.map((s) => s.codec_name), 'chapters:', chapters.length)
+      expect(subs.length, 'an en auto-caption should be embedded').toBeGreaterThan(0)
+      expect(subs[0].codec_name, 'mp4 subtitles convert to mov_text').toBe('mov_text')
+      expect(chapters.length, 'all 3 source chapters should be embedded').toBe(3)
+    },
+    240_000
+  )
+
+  it(
+    'restrictFilenames: output basename is sanitized to a portable ASCII subset',
+    () => {
+      const opts: StartDownloadOptions = {
+        id: 'restrict',
+        url: 'https://www.youtube.com/watch?v=jNQXAC9IVRw', // title "Me at the zoo"
+        kind: 'audio',
+        quality: 'Best'
+      }
+      const options = { ...DEFAULT_DOWNLOAD_OPTIONS, audioFormat: 'mp3' as const, embedThumbnail: false }
+      const access = { ...NO_ACCESS, restrictFilenames: true }
+      // %(title)s so the spaces in "Me at the zoo" actually exercise the sanitizer.
+      const argv = buildArgs(opts, join(outDir, '%(title)s.%(ext)s'), options, BIN_DIR, access)
+      const res = runYtdlp(argv)
+      if (res.status !== 0) console.error('[restrict] stderr:\n' + res.stderr)
+      expect(res.status, 'yt-dlp should exit 0').toBe(0)
+      expect(res.filePath, 'after_move path should be printed').toBeTruthy()
+
+      const base = baseName(res.filePath!)
+      console.log('[restrict] basename:', base)
+      expect(base, 'a restricted filename has no spaces').not.toMatch(/\s/)
+      expect(base, 'restricted to [A-Za-z0-9._-]').toMatch(/^[A-Za-z0-9._-]+$/)
+    },
+    240_000
+  )
+
+  it(
+    'downloadArchive: a second run of the same URL is skipped via the archive',
+    () => {
+      const archive = join(outDir, 'archive.txt')
+      const mk = (id: string): string[] =>
+        buildArgs(
+          { id, url: 'https://www.youtube.com/watch?v=jNQXAC9IVRw', kind: 'audio', quality: 'Best' },
+          join(outDir, 'arch-%(id)s.%(ext)s'),
+          { ...DEFAULT_DOWNLOAD_OPTIONS, audioFormat: 'mp3' as const, embedThumbnail: false },
+          BIN_DIR,
+          { ...NO_ACCESS, downloadArchivePath: archive }
+        )
+
+      const first = runYtdlp(mk('a1'))
+      if (first.status !== 0) console.error('[archive] first stderr:\n' + first.stderr)
+      expect(first.status, 'first run should download').toBe(0)
+      expect(first.filePath, 'first run should produce a file').toBeTruthy()
+      expect(existsSync(archive), 'archive file should be written').toBe(true)
+
+      const second = runYtdlp(mk('a2'))
+      expect(second.status, 'second run should still exit 0').toBe(0)
+      // The id is in the archive, so the second run downloads nothing — and thus
+      // prints no after_move `path|` line. (yt-dlp's "has already been recorded"
+      // notice is itself silenced because buildArgs' --print implies --quiet, so
+      // we assert on the archive contents + the absence of a fresh download.)
+      expect(second.filePath, 'second run should be skipped (no new download)').toBeFalsy()
+      const archiveBody = readFileSync(archive, 'utf8')
+      console.log('[archive] archive.txt:', JSON.stringify(archiveBody.trim()))
+      expect(archiveBody, 'the archive should record the downloaded video id').toContain('jNQXAC9IVRw')
+    },
+    240_000
+  )
+
+  it(
+    'extraArgs (custom command): parseExtraArgs tokens reach yt-dlp (--write-info-json sidecar)',
+    () => {
+      const opts: StartDownloadOptions = {
+        id: 'extra',
+        url: 'https://www.youtube.com/watch?v=jNQXAC9IVRw',
+        kind: 'audio',
+        quality: 'Best'
+      }
+      const options = { ...DEFAULT_DOWNLOAD_OPTIONS, audioFormat: 'mp3' as const, embedThumbnail: false }
+      const extra = parseExtraArgs('--write-info-json --no-mtime')
+      expect(extra, 'parseExtraArgs splits into discrete tokens').toEqual([
+        '--write-info-json',
+        '--no-mtime'
+      ])
+      const argv = buildArgs(opts, join(outDir, 'extra-%(id)s.%(ext)s'), options, BIN_DIR, NO_ACCESS, extra)
+      const res = runYtdlp(argv)
+      if (res.status !== 0) console.error('[extra] stderr:\n' + res.stderr)
+      expect(res.status, 'yt-dlp should exit 0').toBe(0)
+      expect(res.filePath, 'after_move path should be printed').toBeTruthy()
+
+      const infoJson = join(outDir, 'extra-jNQXAC9IVRw.info.json')
+      console.log('[extra] info.json exists:', existsSync(infoJson))
+      expect(existsSync(infoJson), '--write-info-json should write a sidecar').toBe(true)
+    },
+    240_000
+  )
 })