feat(stream): cache extracted subtitles to a hidden .unarr sidecar

On-demand WebVTT extraction re-ran ffmpeg on every /sub request and, for
50GB+ remuxes, couldn't finish a full text track within the 60s HTTP timeout
→ the web player got a 500 and no subtitles.

Extract each text subtitle ONCE — during the library scan (no HTTP deadline,
generous per-file timeout) and write-through on the first on-demand request —
into a hidden ".unarr/<name>.s<index>.vtt" sidecar next to the media file.
The /sub handler serves a fresh sidecar instantly (mtime-invalidated when the
media is replaced), so playback subtitles are instant and huge files work.

- mediainfo.sidecar: cache paths, mtime freshness, atomic write, ExtractSubtitleVTT,
  IsTextSubtitleCodec (shared classifier, mirrors engine + web whitelists).
- library.PrewarmSidecars: bounded, idempotent, ctx-cancellable background pass
  run after every scan (manual + daemon auto-scan).
- subtitleHandler: cache-read → hit; miss → extract → write-through.
- config: library.cache_subtitles (default true), wired via SetCacheSubtitles.

Local-only by design: nothing extracted is uploaded — the sidecar is the user's
own content, private to their disk.
This commit is contained in:
Deivid Soto 2026-06-02 09:10:36 +02:00
parent 7417fad45f
commit 178c16f458
6 changed files with 353 additions and 33 deletions

106
internal/library/prewarm.go Normal file
View file

@ -0,0 +1,106 @@
package library
import (
"context"
"log"
"sync"
"time"
"github.com/torrentclaw/unarr/internal/library/mediainfo"
)
// PrewarmOptions controls scan-time sidecar extraction.
type PrewarmOptions struct {
FFmpegPath string // resolved ffmpeg binary; empty disables prewarm
CacheSubtitles bool // library.cache_subtitles
Workers int // concurrent ffmpeg jobs (each is heavy); default 2
}
// PrewarmSidecars extracts every text subtitle of every scanned item into the
// hidden ".unarr" sidecar dir next to the media file, so the /sub handler serves
// it instantly at play time (instead of re-running ffmpeg, which on a 50GB+
// remux exceeds the on-demand HTTP timeout). Without the per-request 60s ceiling
// here, even huge files complete (generous per-file timeout).
//
// Best-effort and idempotent: an already-fresh sidecar is skipped, errors are
// logged and the item moves on, and ctx cancellation (Ctrl-C / daemon shutdown)
// stops cleanly. Safe to call after every scan — only missing/stale caches do work.
func PrewarmSidecars(ctx context.Context, cache *LibraryCache, opts PrewarmOptions) {
if cache == nil || opts.FFmpegPath == "" || !opts.CacheSubtitles {
return
}
workers := opts.Workers
if workers < 1 {
workers = 2
}
type job struct {
path string
index int
}
jobs := make(chan job)
var wg sync.WaitGroup
var mu sync.Mutex
cached, failed := 0, 0
for i := 0; i < workers; i++ {
wg.Add(1)
go func() {
defer wg.Done()
for j := range jobs {
if ctx.Err() != nil {
return
}
if _, ok := mediainfo.ReadCachedSubtitle(j.path, j.index); ok {
continue // already fresh
}
// Generous per-file deadline: a full text track on a multi-GB
// remux can take minutes to demux. Bounded so one corrupt file
// can't wedge a worker forever.
jctx, cancel := context.WithTimeout(ctx, 10*time.Minute)
vtt, err := mediainfo.ExtractSubtitleVTT(jctx, opts.FFmpegPath, j.path, j.index)
cancel()
if err != nil {
mu.Lock()
failed++
mu.Unlock()
continue
}
if werr := mediainfo.WriteCachedSubtitle(j.path, j.index, vtt); werr != nil {
log.Printf("[prewarm] sidecar write skipped (i=%d path=%q): %v", j.index, j.path, werr)
mu.Lock()
failed++
mu.Unlock()
continue
}
mu.Lock()
cached++
mu.Unlock()
}
}()
}
go func() {
defer close(jobs)
for _, item := range cache.Items {
if item.MediaInfo == nil || item.FilePath == "" {
continue
}
for idx, sub := range item.MediaInfo.Subtitles {
if !mediainfo.IsTextSubtitleCodec(sub.Codec) {
continue // bitmap → burned in, not extractable to WebVTT
}
select {
case jobs <- job{path: item.FilePath, index: idx}:
case <-ctx.Done():
return
}
}
}
}()
wg.Wait()
if cached > 0 || failed > 0 {
log.Printf("[prewarm] subtitles: %d cached, %d failed", cached, failed)
}
}