navidrome/model/metadata/map_mediafile.go
Deluan Quintão 01b7c86f90
fix(scanner): stop logging expected lyrics sniff misses as warnings (#5702)
* fix(scanner): stop logging expected lyrics sniff misses as warnings

During a scan, embedded lyrics are parsed with an empty suffix, which puts
ParseLyrics into content-sniffing mode: it tries the TTML, SRT and Lyricsfile
YAML parsers in turn before falling back to plain text. Every plain-text or LRC
lyric therefore fails the structured probes on its way to the fallback, and each
failure was logged at warning level with no indication of which file triggered
it, flooding the scan log with benign "Error parsing lyrics, falling back to
plain text" messages.

A probe rejecting content it does not own during sniffing is expected control
flow, so it is now logged at trace instead. A parse failure under an explicitly
requested suffix (e.g. a malformed .yaml/.srt/.ttml sidecar) still warns, since
the user declared that format. ParseLyrics gains ctx and path parameters so any
warning names the offending file and carries request context where available;
all call sites are updated accordingly.

Also fixes a test-isolation bug in the new logging spec: the BeforeEach swapped
the process-global default logger via SetDefaultLogger but only restored the log
level on cleanup, leaking the null logger and its hook into later specs in the
shared model suite.

* test: use spec-scoped contexts instead of context.Background in lyrics tests

Replace context.Background() with GinkgoT().Context() (and b.Context() in the
parse benchmarks) across the lyrics-related tests, so contexts are cancelled
when each spec ends. The embeddedLyrics fixture in core/lyrics is now a
hand-written literal like its sibling fixtures, removing the construction-time
ParseLyrics call that could not use a spec-scoped context.

* refactor(model): attach lyrics parse log attribution via context

Narrow ParseLyrics back to (ctx, suffix, lang, contents), dropping the path
parameter added by the previous commit. Attribution now uses the codebase's
existing idiom: callers that know the source attach it with log.NewContext
(e.g. "file" for the media file or sidecar), and the plugin adapter tags both
the plugin name and the track, fixing probe-miss logs that misattributed
plugin-returned content to the file's own tags. This removes three adjacent
string parameters that were easy to swap silently, and the "" placeholder most
call sites had to pass.

Also hardens the logging spec from the previous commit: the null test logger is
now swapped in before raising the level (SetLevel forces the current default
logger to trace, so the old order left the null logger at info and trace
entries never reached the hook), the sniff test now asserts probe misses are
observable at trace with file attribution instead of only asserting the absence
of warnings, and cleanup restores the actual previous logger — via a new return
value on log.SetDefaultLogger — instead of a bare logrus.New() that would
discard hooks configured on the process-wide logger.

* refactor(lyrics): hoist attributed log contexts out of loops

Address review feedback on #5702: build the log-attributed context once per
operation instead of per iteration, and reuse it on the surrounding log calls
so the error/trace lines around ParseLyrics carry the same attribution fields.
In fromExternalFile the sidecar path now rides the context for all log lines
in the function, replacing the repeated explicit "path" field.

* style(model): pass lyrics parse errors as final log arguments

Per the project logging convention, errors go as the last argument (the log
package normalizes them via its error case) instead of a keyed "error" pair,
which stores the raw error value and bypasses that handling. Flagged by review
on #5702; the keyed form was inherited from the original warning line.
2026-07-02 09:46:57 -04:00

197 lines
5.8 KiB
Go

package metadata
import (
"cmp"
"context"
"encoding/json"
"maps"
"math"
"strconv"
"github.com/navidrome/navidrome/conf"
"github.com/navidrome/navidrome/log"
"github.com/navidrome/navidrome/model"
"github.com/navidrome/navidrome/utils/str"
)
func (md Metadata) ToMediaFile(libID int, folderID string) model.MediaFile {
mf := model.MediaFile{
LibraryID: libID,
FolderID: folderID,
Tags: maps.Clone(md.tags),
}
// Title and Album
mf.Title = md.mapTrackTitle()
mf.Album = md.mapAlbumName()
mf.SortTitle = md.String(model.TagTitleSort)
mf.SortAlbumName = md.String(model.TagAlbumSort)
mf.OrderTitle = str.SanitizeFieldForSorting(mf.Title)
mf.OrderAlbumName = str.SanitizeFieldForSortingNoArticle(mf.Album)
mf.Compilation = md.Bool(model.TagCompilation)
// Disc and Track info
mf.TrackNumber, _ = md.NumAndTotal(model.TagTrackNumber)
mf.DiscNumber, _ = md.NumAndTotal(model.TagDiscNumber)
mf.DiscSubtitle = md.String(model.TagDiscSubtitle)
mf.CatalogNum = md.String(model.TagCatalogNumber)
mf.Comment = md.String(model.TagComment)
if f := md.NullableFloat(model.TagBPM); f != nil {
if v := int(math.Round(*f)); v != 0 {
mf.BPM = new(v)
}
}
mf.Lyrics = md.mapLyrics()
mf.ExplicitStatus = md.mapExplicitStatusTag()
// Dates
date, origDate, relDate := md.mapDates()
mf.OriginalYear, mf.OriginalDate = origDate.Year(), string(origDate)
mf.ReleaseYear, mf.ReleaseDate = relDate.Year(), string(relDate)
mf.Year, mf.Date = date.Year(), string(date)
// MBIDs
mf.MbzRecordingID = md.String(model.TagMusicBrainzRecordingID)
mf.MbzReleaseTrackID = md.String(model.TagMusicBrainzTrackID)
mf.MbzAlbumID = md.String(model.TagMusicBrainzAlbumID)
mf.MbzReleaseGroupID = md.String(model.TagMusicBrainzReleaseGroupID)
mf.MbzAlbumType = md.String(model.TagReleaseType)
// ReplayGain
mf.RGAlbumPeak = md.NullableFloat(model.TagReplayGainAlbumPeak)
mf.RGAlbumGain = md.mapGain(model.TagReplayGainAlbumGain, model.TagR128AlbumGain)
mf.RGTrackPeak = md.NullableFloat(model.TagReplayGainTrackPeak)
mf.RGTrackGain = md.mapGain(model.TagReplayGainTrackGain, model.TagR128TrackGain)
// General properties
mf.HasCoverArt = md.HasPicture()
mf.Duration = md.Length()
mf.BitRate = md.AudioProperties().BitRate
mf.SampleRate = md.AudioProperties().SampleRate
if bd := md.AudioProperties().BitDepth; bd > 0 {
mf.BitDepth = new(bd)
}
mf.Channels = md.AudioProperties().Channels
mf.Codec = md.AudioProperties().Codec
mf.Path = md.FilePath()
mf.Suffix = md.Suffix()
mf.Size = md.Size()
mf.BirthTime = md.BirthTime()
mf.UpdatedAt = md.ModTime()
mf.Participants = md.mapParticipants()
mf.Artist = md.mapDisplayArtist()
mf.AlbumArtist = md.mapDisplayAlbumArtist(mf)
// Persistent IDs
mf.PID = md.trackPID(mf)
mf.AlbumID = md.albumID(mf, conf.Server.PID.Album)
// BFR These IDs will go away once the UI handle multiple participants.
// BFR For Legacy Subsonic compatibility, we will set them in the API handlers
mf.ArtistID = mf.Participants.First(model.RoleArtist).ID
mf.AlbumArtistID = mf.Participants.First(model.RoleAlbumArtist).ID
// BFR What to do with sort/order artist names?
mf.OrderArtistName = mf.Participants.First(model.RoleArtist).OrderArtistName
mf.OrderAlbumArtistName = mf.Participants.First(model.RoleAlbumArtist).OrderArtistName
mf.SortArtistName = mf.Participants.First(model.RoleArtist).SortArtistName
mf.SortAlbumArtistName = mf.Participants.First(model.RoleAlbumArtist).SortArtistName
// Don't store tags that are first-class fields (and are not album-level tags) in the
// MediaFile struct. This is to avoid redundancy in the DB
//
// Remove all tags from the main section that are not flagged as album tags
for tag, conf := range model.TagMainMappings() {
if !conf.Album {
delete(mf.Tags, tag)
}
}
return mf
}
func (md Metadata) AlbumID(mf model.MediaFile, pidConf string) string {
return md.albumID(mf, pidConf)
}
func (md Metadata) mapGain(rg, r128 model.TagName) *float64 {
v := md.Gain(rg)
if v != nil {
return v
}
r128value := md.String(r128)
if r128value != "" {
var v, err = strconv.Atoi(r128value)
if err != nil {
return nil
}
// Convert Q7.8 to float
value := float64(v) / 256.0
// Adding 5 dB to normalize with ReplayGain level
value += 5
return &value
}
return nil
}
func (md Metadata) mapLyrics() string {
rawLyrics := md.Pairs(model.TagLyrics)
lyricList := make(model.LyricList, 0, len(rawLyrics))
ctx := log.NewContext(context.Background(), "file", md.filePath)
for _, raw := range rawLyrics {
lang := raw.Key()
text := raw.Value()
lyrics, err := model.ParseLyrics(ctx, "", lang, []byte(text))
if err != nil {
log.Warn(ctx, "Unexpected failure occurred when parsing lyrics", err)
continue
}
for _, lyric := range lyrics {
if !lyric.IsEmpty() {
lyricList = append(lyricList, lyric)
}
}
}
res, err := json.Marshal(lyricList)
if err != nil {
log.Warn("Unexpected error occurred when serializing lyrics", "file", md.filePath, err)
return ""
}
return string(res)
}
func (md Metadata) mapExplicitStatusTag() string {
switch md.first(model.TagExplicitStatus) {
case "1", "4":
return "e"
case "2":
return "c"
default:
return ""
}
}
func (md Metadata) mapDates() (date Date, originalDate Date, releaseDate Date) {
// Start with defaults
date = md.Date(model.TagRecordingDate)
originalDate = md.Date(model.TagOriginalDate)
releaseDate = md.Date(model.TagReleaseDate)
// For some historic reason, taggers have been writing the Release Date of an album to the Date tag,
// and leave the Release Date tag empty.
legacyMappings := (originalDate != "") &&
(releaseDate == "") &&
(date >= originalDate)
if legacyMappings {
return originalDate, originalDate, date
}
// when there's no Date, first fall back to Original Date, then to Release Date.
date = cmp.Or(date, originalDate, releaseDate)
return date, originalDate, releaseDate
}