Files
minstrel/internal/library/duplicate_classify_test.go
T
bvandeusenandClaude Opus 5.5 18d31e9cdd
release / govulncheck (push) Successful in 14s
release / web (push) Successful in 1m21s
release / go (push) Successful in 1m31s
release / android (push) Successful in 5m1s
release / integration (push) Successful in 5m1s
release / Build signed APK (releases and dev) (push) Successful in 5m9s
release / Attach APK to the Release (tag releases only) (push) Skipped
release / Build + push container image (push) Successful in 15s
release / Verify release artifacts (tag releases only) (push) Skipped
feat: one recording cut to several songs' lengths is named by AcoustID; the copy in its slot stays, the rest go, and the release is set aside (#6169)
Savant's Mortals held one recording as 16 of its 50 tracks, each trimmed to
its own slot's MusicBrainz length, so the lengths could not say which slot
was its own and every group waited for the operator. When a one-album
mismatch is the same audio (identical, or fingerprints within 0.02) and
every copy fits its own slot, the resolver asks what the recording is: the
copies' own AcoustID lookups, or a fresh lookup of one copy (five a pass).
The track list names each slot's recording; the copy in that slot is kept
and the others removed, or every copy when the recording is in none of
their slots or AcoustID knows none. AcoustID unreachable or answers in
several copies' slots: the group waits.

Whenever wrong-slot copies are removed, the download the files were
imported from is set aside, so the album fetched again is not the same
files. Albums imported before Minstrel downloaded anything have none.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-20 10:33:55 -04:00

164 lines
8.0 KiB
Go

package library
import (
"fmt"
"testing"
"git.fabledsword.com/bvandeusen/minstrel/internal/db/dbq"
)
// The shapes measured on the operator's library (milestone 498's body).
func TestClassifyDuplicateGroup(t *testing.T) {
m := func(album, title string) ClassifyMember {
return ClassifyMember{AlbumID: album, Title: title, ArtistName: "Gorillaz"}
}
cases := []struct {
name string
tier string
members []ClassifyMember
want DuplicateClass
}{
{"Humanz: one album, one song twice", "exact",
[]ClassifyMember{m("humanz", "Saturnz Barz"), m("humanz", "Saturnz Barz (Official Video)")}, ClassSameRelease},
{"one album, video upload title with artist prefix", "acoustic",
[]ClassifyMember{m("humanz", "Andromeda"), m("humanz", "Gorillaz - Andromeda (Official Audio)")}, ClassSameRelease},
{"one album, identical bytes under a version title: one file in two slots", "exact",
[]ClassifyMember{m("www", "WWW"), m("www", "WWW (instrumental)")}, ClassMismatch},
{"one album, acoustic match, two versions named", "acoustic",
[]ClassifyMember{m("moe", "Lovesick"), m("moe", "Lovesick (Instrumental)")}, ClassDistinct},
{"Void: one album, one audio under three song titles", "acoustic",
[]ClassifyMember{m("void", "Slimewar (into the void)"), m("void", "Void"), m("void", "Reach")}, ClassMismatch},
{"a version named after a dash", "acoustic",
[]ClassifyMember{m("andora", "Goodbye Yesterday"), m("andora", "Goodbye Yesterday - Instrumental Version")}, ClassDistinct},
{"a dash that names no version", "acoustic",
[]ClassifyMember{m("a", "Monday Chill - Part One"), m("a", "Monday Chill - Part Two")}, ClassMismatch},
{"Slasher and Slasher II are not versions of one song", "acoustic",
[]ClassifyMember{m("slasher", "Slasher"), m("slasher", "Slasher II")}, ClassMismatch},
{"Big Me: the single and the album", "exact",
[]ClassifyMember{m("single", "Big Me"), m("album", "Big Me")}, ClassCrossRelease},
{"remaster and featuring credits are one song", "acoustic",
[]ClassifyMember{m("a", "Feel Good Inc. (2017 Remaster)"), m("b", "Feel Good Inc feat. De La Soul")}, ClassCrossRelease},
{"a later release retitles the recording", "acoustic",
[]ClassifyMember{m("coco", "Ragtime Cat"), m("single", "The Ragtime Cat")}, ClassCrossRelease},
{"identical bytes on two albums under two titles", "exact",
[]ClassifyMember{m("dookie", "F.O.D."), m("live", "F.O.D. (live)")}, ClassCrossRelease},
{"a lone copy", "exact", []ClassifyMember{m("a", "Song")}, ClassReview},
}
for _, tc := range cases {
if got := ClassifyDuplicateGroup(tc.tier, tc.members); got != tc.want {
t.Errorf("%s: got %s, want %s", tc.name, got, tc.want)
}
}
}
func TestMatchTitleKey(t *testing.T) {
cases := []struct{ title, artist, want string }{
{"Saturnz Barz (Official Video)", "Gorillaz", "saturnzbarz"},
{"Gorillaz - Saturnz Barz", "Gorillaz", "saturnzbarz"},
{"Doin' It Right (Music Video) ft. Panda Bear", "Daft Punk", "doinitright"},
{"Song [feat. X]", "", "song"},
{"Song - Remastered 2009", "", "song"},
{"Rock & Roll", "", "rockandroll"},
// What names a different recording stays.
{"Song (live)", "", "songlive"},
{"Song (demo)", "", "songdemo"},
{"Song (Remix)", "", "songremix"},
// A title that is nothing but a marker keeps its words rather than vanishing.
{"(Official Video)", "", "officialvideo"},
}
for _, tc := range cases {
if got := MatchTitleKey(tc.title, tc.artist); got != tc.want {
t.Errorf("MatchTitleKey(%q, %q) = %q, want %q", tc.title, tc.artist, got, tc.want)
}
}
}
func TestWrongSlots(t *testing.T) {
track := func(title string, ms int32) dbq.MbReleaseTrack { return dbq.MbReleaseTrack{Title: title, LengthMs: ms} }
copies := func(titles ...string) []slotCopy {
out := make([]slotCopy, len(titles))
for i, title := range titles {
out[i] = slotCopy{Title: title, Artist: "Savant", DurationMs: 220000}
}
return out
}
void := []dbq.MbReleaseTrack{track("Slimewar (Into the Void)", 300000), track("Reach", 281000), track("Void", 220500)}
cases := []struct {
name string
copies []slotCopy
tracks []dbq.MbReleaseTrack
keep int
losers []int
ok bool
}{
{"Void: the file is Void's; the other two slots are other songs", copies("Slimewar (into the void)", "Void", "Reach"), void, 1, []int{0, 2}, true},
{"no track list", copies("Void", "Reach"), nil, -1, nil, false},
{"a title the track list does not hold", copies("Void", "Bonus"), void, -1, nil, false},
{"Killjoy held twice beside Dreamland's slot", []slotCopy{
{Title: "Dreamland", Artist: "Fox Stevenson", DurationMs: 167000},
{Title: "Killjoy", Artist: "Fox Stevenson", DurationMs: 167000},
{Title: "Killjoy", Artist: "Fox Stevenson", DurationMs: 166000},
}, []dbq.MbReleaseTrack{track("Killjoy", 166500), track("Dreamland", 214000)}, 1, []int{0}, true},
{"two slots fit the file", copies("Void", "Reach"), []dbq.MbReleaseTrack{track("Void", 220000), track("Reach", 221500)}, -1, nil, false},
{"a slot near but not within the fit", copies("Void", "Reach"), []dbq.MbReleaseTrack{track("Void", 220000), track("Reach", 226000)}, -1, nil, false},
{"no slot fits, and every slot is clearly another song's", copies("Reach", "Slimewar (into the void)"), void, -1, []int{0, 1}, true},
{"no slot fits, but one is near", copies("Void", "Reach"), []dbq.MbReleaseTrack{track("Void", 226000), track("Reach", 281000)}, -1, nil, false},
{"an unknown length counts for nothing", copies("Void", "Reach"), []dbq.MbReleaseTrack{track("Void", 220000), track("Reach", 0)}, -1, nil, false},
}
for _, tc := range cases {
keep, losers, ok := wrongSlots(tc.copies, tc.tracks)
if keep != tc.keep || ok != tc.ok || fmt.Sprint(losers) != fmt.Sprint(tc.losers) {
t.Errorf("%s: got keep=%d losers=%v ok=%v, want keep=%d losers=%v ok=%v",
tc.name, keep, losers, ok, tc.keep, tc.losers, tc.ok)
}
}
}
// One recording cut to each of several slots' lengths (Savant's Mortals): the
// lengths cannot place it, and what AcoustID calls it does (#6169).
func TestTrimmedCopies(t *testing.T) {
track := func(title string, ms int32, rec string) dbq.MbReleaseTrack {
return dbq.MbReleaseTrack{Title: title, LengthMs: ms, RecordingMbid: rec}
}
copies := []slotCopy{
{Title: "Tormentor", Artist: "The Wombats", DurationMs: 220000},
{Title: "Record Shop", Artist: "The Wombats", DurationMs: 181000},
}
album := []dbq.MbReleaseTrack{
track("Tormentor", 221000, "rec-tormentor"), track("Record Shop", 180000, "rec-record-shop"), track("Ice Cream", 200000, "rec-ice"),
}
if !trimmedToSlots(copies, album) {
t.Fatal("each copy fits its own slot: trimmedToSlots should hold the group")
}
if trimmedToSlots(copies[:1], album) {
t.Error("one title is not several songs' slots")
}
if trimmedToSlots([]slotCopy{copies[0], {Title: "Record Shop", Artist: "The Wombats", DurationMs: 220000}}, album) {
t.Error("a copy that does not fit its slot is wrongSlots' to decide")
}
cases := []struct {
name string
tracks []dbq.MbReleaseTrack
recordings []string
keep int
losers []int
ok bool
}{
{"AcoustID names Tormentor", album, []string{"rec-tormentor"}, 0, []int{1}, true},
{"one of several candidates is on the album", album, []string{"rec-elsewhere", "rec-record-shop"}, 1, []int{0}, true},
{"AcoustID knows none", album, nil, -1, []int{0, 1}, true},
{"the recording is another song on the album", album, []string{"rec-ice"}, -1, []int{0, 1}, true},
{"candidates in both copies' slots", album, []string{"rec-tormentor", "rec-record-shop"}, -1, nil, false},
{"the track list names no recording for a slot", []dbq.MbReleaseTrack{
track("Tormentor", 221000, "rec-tormentor"), track("Record Shop", 180000, ""),
}, []string{"rec-tormentor"}, -1, nil, false},
}
for _, tc := range cases {
keep, losers, ok := trimmedCopies(copies, tc.tracks, tc.recordings)
if keep != tc.keep || ok != tc.ok || fmt.Sprint(losers) != fmt.Sprint(tc.losers) {
t.Errorf("%s: got keep=%d losers=%v ok=%v, want keep=%d losers=%v ok=%v",
tc.name, keep, losers, ok, tc.keep, tc.losers, tc.ok)
}
}
}