navidrome/server/subsonic/media_retrieval.go
Yuuta 3a14faa033
feat(subsonic): add structured sidecar lyrics support with OpenSubsonic v2 karaoke cues and agent layers (#5076)
Expand backend lyrics support with richer sidecar formats and upgrade the
OpenSubsonic songLyrics implementation to the version 2 structured karaoke
contract, while preserving version 1 behavior by default.

Sidecar formats and parsing:
- Add a TTML parser (core/lyrics/ttml.go): clock time, offset time, bare
  decimal seconds, nested timing contexts, and token-level <span> timing for
  word/syllable karaoke. Parses Apple Music-style metadata tracks (translation
  and pronunciation/transliteration) and agent metadata into per-track agents[]
  plus per-cue-line agentId. Hydrates missing line timing from cue timing.
- Add an SRT parser (core/lyrics/srt.go).
- Add a LRCLIB Lyricsfile (.yaml/.yml) parser (model/lyricsfile.go): maps
  per-word lines[].words[] to cues with inclusive UTF-8 byte offsets and
  attributes overlapping lines to synthetic voice agents so parallel vocals
  split correctly in the enhanced response.
- Extend LRC parsing for Enhanced LRC inline <mm:ss.xx> word-timing markers.
- Add UTF-8 BOM and UTF-16 LE support for TTML/LRC sidecars.
- Parse the above formats from embedded tags as well as sidecar files.

Source resolution:
- Default lyricspriority is now
  ".ttml,.yaml,.yml,.elrc,.lrc,.srt,.txt,embedded" so the new formats are
  discoverable without manual configuration.
- Preserve configured source priority across duplicate media-file candidates
  instead of only checking the first DB match, so higher-priority sidecar
  lyrics on older duplicates can still win.
- Raise the embedded-lyrics tag maxLength to 1 MB to fit word-timed
  TTML/Enhanced-LRC karaoke for a full song.

OpenSubsonic songLyrics v2:
- Advertise songLyrics versions [1, 2].
- With enhanced=true, getLyricsBySongId may return structuredLyrics.kind
  (main/translation/pronunciation), cueLine[] line-level karaoke groupings,
  cueLine.cue[] timed words/syllables with required UTF-8 byteStart/byteEnd,
  reusable structuredLyrics.agents[], and cueLine.agentId references.
- Without enhanced=true, the response stays v1-compatible: no kind, no cueLine,
  no agents, no non-main tracks; the existing line[] payload is always
  populated so legacy clients keep working.

Contract details:
- cueLine is emitted only for synced lyrics with cue data.
- Within a cueLine, cue.end is normalized all-or-none and overlaps are removed;
  overlaps across separate cueLines remain valid for parallel vocal layers.
- Missing cue end-times are filled from the next cue or the parent line.
- When cueLines share an index, the one whose agent has role "main" is first.
- LyricCue.Value is serialized as XML chardata; cues with nil start are skipped
  rather than serialized as 0.

Refactoring:
- Move pure format parsers into model/ (lyrics.go, lyrics_ttml.go,
  lyrics_srt.go, lyrics_embedded.go, lyricsfile.go) and extract Subsonic
  response building into server/subsonic/lyrics.go.
- Centralize lyric-kind constants and add Lyrics.EffectiveKind/IsMainKind.
- Add gg.Clone helper.

Spec references:
  https://github.com/opensubsonic/open-subsonic-api/discussions/213
  https://github.com/opensubsonic/open-subsonic-api/pull/218 (songLyrics v2)
  https://github.com/opensubsonic/open-subsonic-api/pull/228 (cue byte offsets)
2026-06-19 12:00:58 -04:00

145 lines
3.8 KiB
Go

package subsonic
import (
"context"
"errors"
"io"
"net/http"
"strings"
"time"
"github.com/navidrome/navidrome/conf"
"github.com/navidrome/navidrome/consts"
"github.com/navidrome/navidrome/log"
"github.com/navidrome/navidrome/model"
"github.com/navidrome/navidrome/resources"
"github.com/navidrome/navidrome/server/subsonic/responses"
"github.com/navidrome/navidrome/utils/gravatar"
"github.com/navidrome/navidrome/utils/req"
)
func (api *Router) GetAvatar(w http.ResponseWriter, r *http.Request) (*responses.Subsonic, error) {
if !conf.Server.EnableGravatar {
return api.getPlaceHolderAvatar(w, r)
}
p := req.Params(r)
username, err := p.String("username")
if err != nil {
return nil, err
}
ctx := r.Context()
u, err := api.ds.User(ctx).FindByUsername(username)
if err != nil {
return nil, err
}
if u.Email == "" {
log.Warn(ctx, "User needs an email for gravatar to work", "username", username)
return api.getPlaceHolderAvatar(w, r)
}
http.Redirect(w, r, gravatar.Url(u.Email, 0), http.StatusFound) //nolint:gosec // URL is not constructed from user input
return nil, nil
}
func (api *Router) getPlaceHolderAvatar(w http.ResponseWriter, r *http.Request) (*responses.Subsonic, error) {
f, err := resources.FS().Open(consts.PlaceholderAvatar)
if err != nil {
log.Error(r, "Image not found", err)
return nil, newError(responses.ErrorDataNotFound, "Avatar image not found")
}
defer f.Close()
_, _ = io.Copy(w, f)
return nil, nil
}
func (api *Router) GetCoverArt(w http.ResponseWriter, r *http.Request) (*responses.Subsonic, error) {
// If context is already canceled, discard request without further processing
if r.Context().Err() != nil {
return nil, nil //nolint:nilerr
}
ctx, cancel := context.WithTimeout(r.Context(), 10*time.Second)
defer cancel()
p := req.Params(r)
id, _ := p.String("id")
size := p.IntOr("size", 0)
square := p.BoolOr("square", false)
imgReader, lastUpdate, err := api.artwork.GetOrPlaceholder(ctx, id, size, square)
switch {
case errors.Is(err, context.Canceled):
return nil, nil
case errors.Is(err, model.ErrNotFound):
log.Warn(r, "Couldn't find coverArt", "id", id, err)
return nil, newError(responses.ErrorDataNotFound, "Artwork not found")
case err != nil:
log.Error(r, "Error retrieving coverArt", "id", id, err)
return nil, err
}
defer imgReader.Close()
w.Header().Set("cache-control", "public, max-age=315360000")
w.Header().Set("last-modified", lastUpdate.Format(http.TimeFormat))
cnt, err := io.Copy(w, imgReader)
if err != nil {
log.Warn(ctx, "Error sending image", "count", cnt, err)
}
return nil, err
}
func (api *Router) GetLyrics(r *http.Request) (*responses.Subsonic, error) {
p := req.Params(r)
artist, _ := p.String("artist")
title, _ := p.String("title")
response := newResponse()
lyricsResponse := responses.Lyrics{}
response.Lyrics = &lyricsResponse
structuredLyrics, err := api.lyrics.GetLyricsByArtistTitle(r.Context(), artist, title)
if err != nil {
return nil, err
}
mainLyric, ok := structuredLyrics.Main()
if !ok {
return response, nil
}
lyricsResponse.Artist = artist
lyricsResponse.Title = title
var lyricsText strings.Builder
for _, line := range mainLyric.Line {
lyricsText.WriteString(line.Value + "\n")
}
lyricsResponse.Value = lyricsText.String()
return response, nil
}
func (api *Router) GetLyricsBySongId(r *http.Request) (*responses.Subsonic, error) {
id, err := req.Params(r).String("id")
if err != nil {
return nil, err
}
mediaFile, err := api.ds.MediaFile(r.Context()).Get(id)
if err != nil {
return nil, err
}
structuredLyrics, err := api.lyrics.GetLyrics(r.Context(), mediaFile)
if err != nil {
return nil, err
}
enhanced, _ := req.Params(r).Bool("enhanced")
response := newResponse()
response.LyricsList = buildLyricsList(mediaFile, structuredLyrics, enhanced)
return response, nil
}