navidrome/scanner/metadata/metadata.go

package metadata

import (
	"fmt"
	"math"
	"os"
	"path"
	"regexp"
	"strconv"
	"strings"
	"time"

	"github.com/google/uuid"
	"github.com/navidrome/navidrome/conf"
	"github.com/navidrome/navidrome/log"
)

type Extractor interface {
	Extract(files ...string) (map[string]*Tags, error)
}

func Extract(files ...string) (map[string]*Tags, error) {
	var e Extractor

	switch conf.Server.Scanner.Extractor {
	case "taglib":
		e = &taglibExtractor{}
	case "ffmpeg":
		e = &ffmpegExtractor{}
	default:
		log.Warn("Invalid Scanner.Extractor option. Using default ffmpeg", "requested", conf.Server.Scanner.Extractor,
			"validOptions", "ffmpeg,taglib")
		e = &ffmpegExtractor{}
	}
	return e.Extract(files...)
}

type Tags struct {
	filePath string
	suffix   string
	fileInfo os.FileInfo
	tags     map[string][]string
	custom   map[string][]string
}

func NewTag(filePath string, tags, custom map[string][]string) *Tags {
	fileInfo, err := os.Stat(filePath)
	if err != nil {
		log.Warn("Error stating file. Skipping", "filePath", filePath, err)
		return nil
	}

	return &Tags{
		filePath: filePath,
		suffix:   strings.ToLower(strings.TrimPrefix(path.Ext(filePath), ".")),
		fileInfo: fileInfo,
		tags:     tags,
		custom:   custom,
	}
}

// Common tags

func (t *Tags) Title() string           { return t.getTag("title", "sort_name", "titlesort") }
func (t *Tags) Album() string           { return t.getTag("album", "sort_album", "albumsort") }
func (t *Tags) Artist() string          { return t.getTag("artist", "sort_artist", "artistsort") }
func (t *Tags) AlbumArtist() string     { return t.getTag("album_artist", "album artist", "albumartist") }
func (t *Tags) SortTitle() string       { return t.getSortTag("", "title", "name") }
func (t *Tags) SortAlbum() string       { return t.getSortTag("", "album") }
func (t *Tags) SortArtist() string      { return t.getSortTag("", "artist") }
func (t *Tags) SortAlbumArtist() string { return t.getSortTag("tso2", "albumartist", "album_artist") }
func (t *Tags) Genre() string           { return t.getTag("genre") }
func (t *Tags) Year() int               { return t.getYear("date") }
func (t *Tags) Comment() string         { return t.getTag("comment") }
func (t *Tags) Lyrics() string          { return t.getTag("lyrics", "lyrics-eng") }
func (t *Tags) Compilation() bool       { return t.getBool("tcmp", "compilation") }
func (t *Tags) TrackNumber() (int, int) { return t.getTuple("track", "tracknumber") }
func (t *Tags) DiscNumber() (int, int)  { return t.getTuple("disc", "discnumber") }
func (t *Tags) DiscSubtitle() string    { return t.getTag("tsst", "discsubtitle", "setsubtitle") }
func (t *Tags) CatalogNum() string      { return t.getTag("catalognumber") }
func (t *Tags) Bpm() int                { return (int)(math.Round(t.getFloat("tbpm", "bpm", "fbpm"))) }
func (t *Tags) HasPicture() bool        { return t.getTag("has_picture") != "" }

// MusicBrainz Identifiers

func (t *Tags) MbzTrackID() string { return t.getMbzID("musicbrainz_trackid", "musicbrainz track id") }
func (t *Tags) MbzAlbumID() string { return t.getMbzID("musicbrainz_albumid", "musicbrainz album id") }
func (t *Tags) MbzArtistID() string {
	return t.getMbzID("musicbrainz_artistid", "musicbrainz artist id")
}
func (t *Tags) MbzAlbumArtistID() string {
	return t.getMbzID("musicbrainz_albumartistid", "musicbrainz album artist id")
}
func (t *Tags) MbzAlbumType() string {
	return t.getTag("musicbrainz_albumtype", "musicbrainz album type")
}
func (t *Tags) MbzAlbumComment() string {
	return t.getTag("musicbrainz_albumcomment", "musicbrainz album comment")
}

// File properties

func (t *Tags) Duration() float32           { return float32(t.getFloat("duration")) }
func (t *Tags) BitRate() int                { return t.getInt("bitrate") }
func (t *Tags) ModificationTime() time.Time { return t.fileInfo.ModTime() }
func (t *Tags) Size() int64                 { return t.fileInfo.Size() }
func (t *Tags) FilePath() string            { return t.filePath }
func (t *Tags) Suffix() string              { return t.suffix }

func (t *Tags) getTags(tags ...string) []string {
	allTags := append(tags, t.custom[tags[0]]...)
	for _, tag := range allTags {
		if v, ok := t.tags[tag]; ok {
			return v
		}
	}
	return nil
}

func (t *Tags) getTag(tags ...string) string {
	ts := t.getTags(tags...)
	if len(ts) > 0 {
		return ts[0]
	}
	return ""
}

func (t *Tags) getSortTag(originalTag string, tags ...string) string {
	formats := []string{"sort%s", "sort_%s", "sort-%s", "%ssort", "%s_sort", "%s-sort"}
	all := []string{originalTag}
	for _, tag := range tags {
		for _, format := range formats {
			name := fmt.Sprintf(format, tag)
			all = append(all, name)
		}
	}
	return t.getTag(all...)
}

var dateRegex = regexp.MustCompile(`([12]\d\d\d)`)

func (t *Tags) getYear(tags ...string) int {
	tag := t.getTag(tags...)
	if tag == "" {
		return 0
	}
	match := dateRegex.FindStringSubmatch(tag)
	if len(match) == 0 {
		log.Warn("Error parsing year date field", "file", t.filePath, "date", tag)
		return 0
	}
	year, _ := strconv.Atoi(match[1])
	return year
}

func (t *Tags) getBool(tags ...string) bool {
	tag := t.getTag(tags...)
	if tag == "" {
		return false
	}
	i, _ := strconv.Atoi(strings.TrimSpace(tag))
	return i == 1
}

func (t *Tags) getTuple(tags ...string) (int, int) {
	tag := t.getTag(tags...)
	if tag == "" {
		return 0, 0
	}
	tuple := strings.Split(tag, "/")
	t1, t2 := 0, 0
	t1, _ = strconv.Atoi(tuple[0])
	if len(tuple) > 1 {
		t2, _ = strconv.Atoi(tuple[1])
	} else {
		t2tag := t.getTag(tags[0] + "total")
		t2, _ = strconv.Atoi(t2tag)
	}
	return t1, t2
}

func (t *Tags) getMbzID(tags ...string) string {
	tag := t.getTag(tags...)
	if _, err := uuid.Parse(tag); err != nil {
		return ""
	}
	return tag
}

func (t *Tags) getInt(tags ...string) int {
	tag := t.getTag(tags...)
	i, _ := strconv.Atoi(tag)
	return i
}

func (t *Tags) getFloat(tags ...string) float64 {
	var tag = t.getTag(tags...)
	var value, err = strconv.ParseFloat(tag, 64)
	if err != nil {
		return 0
	}
	return value
}