Add "inspect" command to CLI

cmd/inspect.go

@@ -0,0 +1,99 @@
+package cmd
+
+import (
+	"encoding/json"
+	"fmt"
+	"strings"
+
+	"github.com/navidrome/navidrome/conf"
+	"github.com/navidrome/navidrome/log"
+	"github.com/navidrome/navidrome/model"
+	"github.com/navidrome/navidrome/scanner"
+	"github.com/navidrome/navidrome/scanner/metadata"
+	"github.com/navidrome/navidrome/tests"
+	"github.com/pelletier/go-toml/v2"
+	"github.com/spf13/cobra"
+	"gopkg.in/yaml.v3"
+)
+
+var (
+	extractor string
+	format    string
+)
+
+func init() {
+	inspectCmd.Flags().StringVarP(&extractor, "extractor", "x", "", "extractor to use (ffmpeg or taglib, default: auto)")
+	inspectCmd.Flags().StringVarP(&format, "format", "f", "pretty", "output format (pretty, toml, yaml, json, jsonindent)")
+	rootCmd.AddCommand(inspectCmd)
+}
+
+var inspectCmd = &cobra.Command{
+	Use:   "inspect [files to inspect]",
+	Short: "Inspect tags",
+	Long:  "Show file tags as seen by Navidrome",
+	Args:  cobra.MinimumNArgs(1),
+	Run: func(cmd *cobra.Command, args []string) {
+		runInspector(args)
+	},
+}
+
+var marshalers = map[string]func(interface{}) ([]byte, error){
+	"pretty": prettyMarshal,
+	"toml":   toml.Marshal,
+	"yaml":   yaml.Marshal,
+	"json":   json.Marshal,
+	"jsonindent": func(v interface{}) ([]byte, error) {
+		return json.MarshalIndent(v, "", "  ")
+	},
+}
+
+func prettyMarshal(v interface{}) ([]byte, error) {
+	out := v.([]inspectorOutput)
+	var res strings.Builder
+	for i := range out {
+		res.WriteString(fmt.Sprintf("====================\nFile: %s\n\n", out[i].File))
+		t, _ := toml.Marshal(out[i].RawTags)
+		res.WriteString(fmt.Sprintf("Raw tags:\n%s\n\n", t))
+		t, _ = toml.Marshal(out[i].MappedTags)
+		res.WriteString(fmt.Sprintf("Mapped tags:\n%s\n\n", t))
+	}
+	return []byte(res.String()), nil
+}
+
+type inspectorOutput struct {
+	File       string
+	RawTags    metadata.ParsedTags
+	MappedTags model.MediaFile
+}
+
+func runInspector(args []string) {
+	if extractor != "" {
+		conf.Server.Scanner.Extractor = extractor
+	}
+	log.Info("Using extractor", "extractor", conf.Server.Scanner.Extractor)
+	md, err := metadata.Extract(args...)
+	if err != nil {
+		log.Fatal("Error extracting tags", err)
+	}
+	mapper := scanner.NewMediaFileMapper(conf.Server.MusicFolder, &tests.MockedGenreRepo{})
+	marshal := marshalers[format]
+	if marshal == nil {
+		log.Fatal("Invalid format", "format", format)
+	}
+	var out []inspectorOutput
+	for k, v := range md {
+		if !model.IsAudioFile(k) {
+			continue
+		}
+		if len(v.Tags) == 0 {
+			continue
+		}
+		out = append(out, inspectorOutput{
+			File:       k,
+			RawTags:    v.Tags,
+			MappedTags: mapper.ToMediaFile(v),
+		})
+	}
+	data, _ := marshal(out)
+	fmt.Println(string(data))
+}

scanner/mapping.go

@@ -15,20 +15,20 @@ import (
 	"github.com/navidrome/navidrome/utils"
 )
 
-type mediaFileMapper struct {
+type MediaFileMapper struct {
 	rootFolder string
 	genres     model.GenreRepository
 }
 
-func newMediaFileMapper(rootFolder string, genres model.GenreRepository) *mediaFileMapper {
+func NewMediaFileMapper(rootFolder string, genres model.GenreRepository) *MediaFileMapper {
-	return &mediaFileMapper{
+	return &MediaFileMapper{
 		rootFolder: rootFolder,
 		genres:     genres,
 	}
 }
 
 // TODO Move most of these mapping functions to setters in the model.MediaFile
-func (s mediaFileMapper) toMediaFile(md metadata.Tags) model.MediaFile {
+func (s MediaFileMapper) ToMediaFile(md metadata.Tags) model.MediaFile {
 	mf := &model.MediaFile{}
 	mf.ID = s.trackID(md)
 	mf.Year, mf.Date, mf.OriginalYear, mf.OriginalDate, mf.ReleaseYear, mf.ReleaseDate = s.mapDates(md)
@@ -86,7 +86,7 @@ func sanitizeFieldForSorting(originalValue string) string {
 	return utils.NoArticle(v)
 }
 
-func (s mediaFileMapper) mapTrackTitle(md metadata.Tags) string {
+func (s MediaFileMapper) mapTrackTitle(md metadata.Tags) string {
 	if md.Title() == "" {
 		s := strings.TrimPrefix(md.FilePath(), s.rootFolder+string(os.PathSeparator))
 		e := filepath.Ext(s)
@@ -95,7 +95,7 @@ func (s mediaFileMapper) mapTrackTitle(md metadata.Tags) string {
 	return md.Title()
 }
 
-func (s mediaFileMapper) mapAlbumArtistName(md metadata.Tags) string {
+func (s MediaFileMapper) mapAlbumArtistName(md metadata.Tags) string {
 	switch {
 	case md.AlbumArtist() != "":
 		return md.AlbumArtist()
@@ -108,14 +108,14 @@ func (s mediaFileMapper) mapAlbumArtistName(md metadata.Tags) string {
 	}
 }
 
-func (s mediaFileMapper) mapArtistName(md metadata.Tags) string {
+func (s MediaFileMapper) mapArtistName(md metadata.Tags) string {
 	if md.Artist() != "" {
 		return md.Artist()
 	}
 	return consts.UnknownArtist
 }
 
-func (s mediaFileMapper) mapAlbumName(md metadata.Tags) string {
+func (s MediaFileMapper) mapAlbumName(md metadata.Tags) string {
 	name := md.Album()
 	if name == "" {
 		return consts.UnknownAlbum
@@ -123,11 +123,11 @@ func (s mediaFileMapper) mapAlbumName(md metadata.Tags) string {
 	return name
 }
 
-func (s mediaFileMapper) trackID(md metadata.Tags) string {
+func (s MediaFileMapper) trackID(md metadata.Tags) string {
 	return fmt.Sprintf("%x", md5.Sum([]byte(md.FilePath())))
 }
 
-func (s mediaFileMapper) albumID(md metadata.Tags, releaseDate string) string {
+func (s MediaFileMapper) albumID(md metadata.Tags, releaseDate string) string {
 	albumPath := strings.ToLower(fmt.Sprintf("%s\\%s", s.mapAlbumArtistName(md), s.mapAlbumName(md)))
 	if !conf.Server.Scanner.GroupAlbumReleases {
 		if len(releaseDate) != 0 {
@@ -137,15 +137,15 @@ func (s mediaFileMapper) albumID(md metadata.Tags, releaseDate string) string {
 	return fmt.Sprintf("%x", md5.Sum([]byte(albumPath)))
 }
 
-func (s mediaFileMapper) artistID(md metadata.Tags) string {
+func (s MediaFileMapper) artistID(md metadata.Tags) string {
 	return fmt.Sprintf("%x", md5.Sum([]byte(strings.ToLower(s.mapArtistName(md)))))
 }
 
-func (s mediaFileMapper) albumArtistID(md metadata.Tags) string {
+func (s MediaFileMapper) albumArtistID(md metadata.Tags) string {
 	return fmt.Sprintf("%x", md5.Sum([]byte(strings.ToLower(s.mapAlbumArtistName(md)))))
 }
 
-func (s mediaFileMapper) mapGenres(genres []string) (string, model.Genres) {
+func (s MediaFileMapper) mapGenres(genres []string) (string, model.Genres) {
 	var result model.Genres
 	unique := map[string]struct{}{}
 	var all []string
@@ -174,7 +174,7 @@ func (s mediaFileMapper) mapGenres(genres []string) (string, model.Genres) {
 	return result[0].Name, result
 }
 
-func (s mediaFileMapper) mapDates(md metadata.Tags) (year int, date string,
+func (s MediaFileMapper) mapDates(md metadata.Tags) (year int, date string,
 	originalYear int, originalDate string,
 	releaseYear int, releaseDate string) {
 	// Start with defaults

scanner/mapping_internal_test.go

@@ -12,11 +12,11 @@ import (
 )
 
 var _ = Describe("mapping", func() {
-	Describe("mediaFileMapper", func() {
+	Describe("MediaFileMapper", func() {
-		var mapper *mediaFileMapper
+		var mapper *MediaFileMapper
 		Describe("mapTrackTitle", func() {
 			BeforeEach(func() {
-				mapper = newMediaFileMapper("/music", nil)
+				mapper = NewMediaFileMapper("/music", nil)
 			})
 			It("returns the Title when it is available", func() {
 				md := metadata.NewTag("/music/artist/album01/Song.mp3", nil, metadata.ParsedTags{"title": []string{"This is not a love song"}})
@@ -37,7 +37,7 @@ var _ = Describe("mapping", func() {
 				ds := &tests.MockDataStore{}
 				gr = ds.Genre(ctx)
 				gr = newCachedGenreRepository(ctx, gr)
-				mapper = newMediaFileMapper("/", gr)
+				mapper = NewMediaFileMapper("/", gr)
 			})
 
 			It("returns empty if no genres are available", func() {
@@ -79,7 +79,7 @@ var _ = Describe("mapping", func() {
 		Describe("mapDates", func() {
 			var md metadata.Tags
 			BeforeEach(func() {
-				mapper = newMediaFileMapper("/", nil)
+				mapper = NewMediaFileMapper("/", nil)
 			})
 			Context("when all date fields are provided", func() {
 				BeforeEach(func() {

scanner/metadata/metadata.go

@@ -58,25 +58,35 @@ func Extract(files ...string) (map[string]Tags, error) {
 
 func NewTag(filePath string, fileInfo os.FileInfo, tags ParsedTags) Tags {
 	for t, values := range tags {
-		tags[t] = removeDuplicates(values)
+		values = removeDuplicatesAndEmpty(values)
+		if len(values) == 0 {
+			delete(tags, t)
+			continue
+		}
+		tags[t] = values
 	}
 	return Tags{
 		filePath: filePath,
 		fileInfo: fileInfo,
-		tags:     tags,
+		Tags:     tags,
 	}
 }
 
-func removeDuplicates(values []string) []string {
+func removeDuplicatesAndEmpty(values []string) []string {
 	encountered := map[string]struct{}{}
+	empty := true
 	var result []string
 	for _, v := range values {
 		if _, ok := encountered[v]; ok {
 			continue
 		}
 		encountered[v] = struct{}{}
+		empty = empty && v == ""
 		result = append(result, v)
 	}
+	if empty {
+		return nil
+	}
 	return result
 }
 
@@ -100,7 +110,7 @@ func (p ParsedTags) Map(customMappings ParsedTags) ParsedTags {
 type Tags struct {
 	filePath string
 	fileInfo os.FileInfo
-	tags     ParsedTags
+	Tags     ParsedTags
 }
 
 // Common tags
@@ -207,7 +217,7 @@ func (t Tags) getPeakValue(tagName string) float64 {
 
 func (t Tags) getTags(tagNames ...string) []string {
 	for _, tag := range tagNames {
-		if v, ok := t.tags[tag]; ok {
+		if v, ok := t.Tags[tag]; ok {
 			return v
 		}
 	}
@@ -225,7 +235,7 @@ func (t Tags) getFirstTagValue(tagNames ...string) string {
 func (t Tags) getAllTagValues(tagNames ...string) []string {
 	var values []string
 	for _, tag := range tagNames {
-		if v, ok := t.tags[tag]; ok {
+		if v, ok := t.Tags[tag]; ok {
 			values = append(values, v...)
 		}
 	}

scanner/metadata/metadata_internal_test.go

@@ -9,7 +9,7 @@ var _ = Describe("Tags", func() {
 	DescribeTable("getDate",
 		func(tag string, expectedYear int, expectedDate string) {
 			md := &Tags{}
-			md.tags = map[string][]string{"date": {tag}}
+			md.Tags = map[string][]string{"date": {tag}}
 			testYear, testDate := md.Date()
 			Expect(testYear).To(Equal(expectedYear))
 			Expect(testDate).To(Equal(expectedDate))
@@ -29,7 +29,7 @@ var _ = Describe("Tags", func() {
 	Describe("getMbzID", func() {
 		It("return a valid MBID", func() {
 			md := &Tags{}
-			md.tags = map[string][]string{
+			md.Tags = map[string][]string{
 				"musicbrainz_trackid":        {"8f84da07-09a0-477b-b216-cc982dabcde1"},
 				"musicbrainz_releasetrackid": {"6caf16d3-0b20-3fe6-8020-52e31831bc11"},
 				"musicbrainz_albumid":        {"f68c985d-f18b-4f4a-b7f0-87837cf3fbf9"},
@@ -44,7 +44,7 @@ var _ = Describe("Tags", func() {
 		})
 		It("return empty string for invalid MBID", func() {
 			md := &Tags{}
-			md.tags = map[string][]string{
+			md.Tags = map[string][]string{
 				"musicbrainz_trackid":       {"11406732-6"},
 				"musicbrainz_albumid":       {"11406732"},
 				"musicbrainz_artistid":      {"200455"},
@@ -60,7 +60,7 @@ var _ = Describe("Tags", func() {
 	Describe("getAllTagValues", func() {
 		It("returns values from all tag names", func() {
 			md := &Tags{}
-			md.tags = map[string][]string{
+			md.Tags = map[string][]string{
 				"genre": {"Rock", "Pop", "New Wave"},
 			}
 
@@ -68,23 +68,31 @@ var _ = Describe("Tags", func() {
 		})
 	})
 
-	Describe("removeDuplicates", func() {
+	Describe("removeDuplicatesAndEmpty", func() {
 		It("removes duplicates", func() {
 			md := NewTag("/music/artist/album01/Song.mp3", nil, ParsedTags{
 				"genre": []string{"pop", "rock", "pop"},
 				"date":  []string{"2023-03-01", "2023-03-01"},
 				"mood":  []string{"happy", "sad"},
 			})
-			Expect(md.tags).To(HaveKeyWithValue("genre", []string{"pop", "rock"}))
+			Expect(md.Tags).To(HaveKeyWithValue("genre", []string{"pop", "rock"}))
-			Expect(md.tags).To(HaveKeyWithValue("date", []string{"2023-03-01"}))
+			Expect(md.Tags).To(HaveKeyWithValue("date", []string{"2023-03-01"}))
-			Expect(md.tags).To(HaveKeyWithValue("mood", []string{"happy", "sad"}))
+			Expect(md.Tags).To(HaveKeyWithValue("mood", []string{"happy", "sad"}))
+		})
+		It("removes empty tags", func() {
+			md := NewTag("/music/artist/album01/Song.mp3", nil, ParsedTags{
+				"genre": []string{"pop", "rock", "pop"},
+				"mood":  []string{"", ""},
+			})
+			Expect(md.Tags).To(HaveKeyWithValue("genre", []string{"pop", "rock"}))
+			Expect(md.Tags).ToNot(HaveKey("mood"))
 		})
 	})
 
 	Describe("Bpm", func() {
 		var t *Tags
 		BeforeEach(func() {
-			t = &Tags{tags: map[string][]string{
+			t = &Tags{Tags: map[string][]string{
 				"fbpm": []string{"141.7"},
 			}}
 		})

scanner/tag_scanner.go

@@ -27,7 +27,7 @@ type TagScanner struct {
 	ds          model.DataStore
 	plsSync     *playlistImporter
 	cnt         *counters
-	mapper      *mediaFileMapper
+	mapper      *MediaFileMapper
 	cacheWarmer artwork.CacheWarmer
 }
 
@@ -100,7 +100,7 @@ func (s *TagScanner) Scan(ctx context.Context, lastModifiedSince time.Time, prog
 	var changedDirs []string
 	s.cnt = &counters{}
 	genres := newCachedGenreRepository(ctx, s.ds.Genre(ctx))
-	s.mapper = newMediaFileMapper(s.rootFolder, genres)
+	s.mapper = NewMediaFileMapper(s.rootFolder, genres)
 	refresher := newRefresher(s.ds, s.cacheWarmer, allFSDirs)
 
 	log.Trace(ctx, "Loading directory tree from music folder", "folder", s.rootFolder)
@@ -386,7 +386,7 @@ func (s *TagScanner) loadTracks(filePaths []string) (model.MediaFiles, error) {
 
 	var mfs model.MediaFiles
 	for _, md := range mds {
-		mf := s.mapper.toMediaFile(md)
+		mf := s.mapper.ToMediaFile(md)
 		mfs = append(mfs, mf)
 	}
 	return mfs, nil