minstrel/internal/library/duplicate_classify.go

package library

import (
	"regexp"
	"strings"
	"unicode"
)

// Duplicate classification (M498 #5435).
//
// A duplicate group is one recording found more than once. What should happen
// to it depends on where the copies sit, and the measured library (milestone
// 498's body) splits into four shapes:
//
//   - same_release: every copy is on one album. An album holds a song once, so
//     the extra copies are the ones to fold away.
//   - cross_release: the copies are on different albums under one title. A
//     single and the album it came from, a deluxe edition and the standard one:
//     each copy belongs to its own release, so none is deleted (unless it is a
//     video rip; the resolver decides).
//   - mismatch: byte-identical audio on different albums under different
//     titles. One file carries another song's tags — a wrong-file import.
//   - review: anything else. The operator decides.

// DuplicateClass is a group's shape. The values are duplicate_groups.class.
type DuplicateClass string

const (
	ClassSameRelease  DuplicateClass = "same_release"
	ClassCrossRelease DuplicateClass = "cross_release"
	ClassMismatch     DuplicateClass = "mismatch"
	ClassReview       DuplicateClass = "review"
)

// ClassifyMember is what classifying needs to know about one copy.
type ClassifyMember struct {
	AlbumID    string
	Title      string
	ArtistName string
}

// ClassifyDuplicateGroup decides a group's shape from its tier ("exact" or
// "acoustic") and its copies.
//
// Titles are compared by MatchTitleKey, which drops what a release or an upload
// adds to a title (featuring credits, remaster notes, video markers) and keeps
// what names a different recording (live, demo, remix, instrumental). So one
// album holding "WWW" and "WWW (instrumental)" as an acoustic match is review,
// not a copy to fold away: the #3885 case, where they were in fact different
// recordings mislabelled. Byte-identical copies on one album are the same file
// twice whatever their tags say.
func ClassifyDuplicateGroup(tier string, members []ClassifyMember) DuplicateClass {
	if len(members) < 2 {
		return ClassReview
	}
	oneAlbum, oneTitle := true, true
	key := MatchTitleKey(members[0].Title, members[0].ArtistName)
	for _, m := range members[1:] {
		if m.AlbumID != members[0].AlbumID {
			oneAlbum = false
		}
		if MatchTitleKey(m.Title, m.ArtistName) != key {
			oneTitle = false
		}
	}
	exact := tier == string(tierExact)
	switch {
	case oneAlbum && (oneTitle || exact):
		return ClassSameRelease
	case oneAlbum:
		return ClassReview
	case oneTitle:
		return ClassCrossRelease
	case exact:
		return ClassMismatch
	default:
		return ClassReview
	}
}

var (
	// A bracketed credit: "(feat. Panda Bear)", "[ft. X]", "(featuring Y)".
	featBracket = regexp.MustCompile(`(?i)[(\[][^)\]]*\b(feat\.?|ft\.?|featuring)\s[^)\]]*[)\]]`)
	// A credit trailing the title without brackets: "Doin' It Right ft. Panda Bear".
	featTrailing = regexp.MustCompile(`(?i)\s(feat\.?|ft\.?|featuring)\s.*$`)
	// "(2011 Remaster)", "[Remastered]", "- Remastered 2009".
	remasterBracket = regexp.MustCompile(`(?i)[(\[][^)\]]*remaster[^)\]]*[)\]]`)
	remasterSuffix  = regexp.MustCompile(`(?i)\s-\s[^-]*remaster.*$`)
	// Any bracketed segment, to test each against the video-rip markers.
	bracketed = regexp.MustCompile(`[(\[][^)\]]*[)\]]`)
)

// MatchTitleKey reduces a title to what identifies the song, for deciding
// whether two copies carry the same one.
//
// Dropped: a leading "Artist - " (a video upload's title), bracketed featuring
// credits and remaster notes, and bracketed segments carrying a video-rip marker
// ("(Official Video)", "[HD]"). Kept: every other bracketed word, so "(live)",
// "(demo)", "(acoustic)", "(remix)" and "(instrumental)" still tell recordings
// apart. Then case, "&" against "and", and punctuation and spacing are ignored.
func MatchTitleKey(title, artist string) string {
	t := strings.TrimSpace(title)
	if a := strings.TrimSpace(artist); a != "" {
		if prefix := a + " - "; len(t) > len(prefix) && strings.EqualFold(t[:len(prefix)], prefix) {
			t = t[len(prefix):]
		}
	}
	t = featBracket.ReplaceAllString(t, " ")
	t = remasterBracket.ReplaceAllString(t, " ")
	t = bracketed.ReplaceAllStringFunc(t, func(seg string) string {
		for _, re := range suspectSourceRegexps {
			if re.MatchString(seg) {
				return " "
			}
		}
		return seg
	})
	t = remasterSuffix.ReplaceAllString(t, "")
	t = featTrailing.ReplaceAllString(t, "")
	if key := alnumKey(t); key != "" {
		return key
	}
	return alnumKey(title)
}

// alnumKey lowercases, reads "&" as "and", and keeps only letters and digits.
func alnumKey(s string) string {
	s = strings.ReplaceAll(strings.ToLower(s), "&", " and ")
	var b strings.Builder
	for _, r := range s {
		if unicode.IsLetter(r) || unicode.IsDigit(r) {
			b.WriteRune(r)
		}
	}
	return b.String()
}