feat: recommend from Deezer and YouTube Music radios
- Deezer: /artist/{id}/radio for collection artists, affinity 2.0
- YouTube Music: RDAMVM watch playlist via yt-dlp, affinity 2.0
- seed radios from the 2 newest songs of the mood's own catalog
- dedupe candidates by recording, not only by external id
- clean raw YouTube titles and Topic suffixes when indexing
- tests, smoke marker for the RDAMVM path, docs
This commit is contained in:
1 parent
62bcefad20
commit
26c41cc7d9
12 files changed
+296
-44
No files matched your search
@@ -45,6 +45,8 @@ class DiscoveryService(
|
||||
val seeds = DiscoverySeeds(
|
||||
artists = artists,
|
||||
albums = albums,
|
||||
// Only songs from the mood's own catalog can seed its radio.
|
||||
trackIds = radioSeedIds(collection, mood.source, RADIO_SEEDS),
|
||||
hint = mood.query,
|
||||
genres = mood.genres,
|
||||
name = mood.name,
|
||||
@@ -95,14 +97,10 @@ class DiscoveryService(
|
||||
return DiscoveryOutcome(0, error = message)
|
||||
}
|
||||
|
||||
val candidates = LinkedHashMap<String, TrackCandidate>()
|
||||
(searches.mapNotNull { it.getOrNull() }.flatten() + discovered).forEach { candidate ->
|
||||
if (!isMusicLength(candidate.duration)) return@forEach
|
||||
val existing = candidates[candidate.externalId]
|
||||
if (existing == null || existing.affinity < candidate.affinity) {
|
||||
candidates[candidate.externalId] = candidate
|
||||
}
|
||||
}
|
||||
val candidates = mergeCandidates(
|
||||
(searches.mapNotNull { it.getOrNull() }.flatten() + discovered)
|
||||
.filter { isMusicLength(it.duration) },
|
||||
)
|
||||
|
||||
if (candidates.isEmpty()) {
|
||||
val message = "${catalog.source} returned no usable results"
|
||||
@@ -118,6 +116,10 @@ class DiscoveryService(
|
||||
.toSet()
|
||||
|
||||
val moodText = listOfNotNull(mood.query, mood.description, mood.name).joinToString(" ")
|
||||
// A different upload of a song already in the mood is still a duplicate.
|
||||
val collectionRecordings = collection
|
||||
.map { recordingKey(it.artist, it.title) }
|
||||
.toSet()
|
||||
val artistWeights = artists
|
||||
.associate { matchKey(it.name) to it.songs.toDouble() }
|
||||
.filterKeys { it.isNotEmpty() }
|
||||
@@ -129,6 +131,7 @@ class DiscoveryService(
|
||||
val ranked = rankCandidates(
|
||||
candidates.values
|
||||
.filterNot { it.externalId in excluded }
|
||||
.filterNot { recordingKey(it.artist, it.title) in collectionRecordings }
|
||||
.map { candidate ->
|
||||
candidate to scoreCandidate(candidate, artistWeights, albumKeys, moodText)
|
||||
},
|
||||
@@ -175,6 +178,7 @@ class DiscoveryService(
|
||||
|
||||
/** The graph expands far more than a single search page does. */
|
||||
const val DISCOVERY_LIMIT = 200
|
||||
const val RADIO_SEEDS = 2
|
||||
const val CANDIDATE_POOL = 60
|
||||
}
|
||||
}
|
||||
@@ -216,6 +220,20 @@ internal fun artistsByFrequency(collection: List<SongRecord>): List<SeedArtist>
|
||||
)
|
||||
.map { SeedArtist(it.key, it.value) }
|
||||
|
||||
/**
|
||||
* The most recent `(source, externalId)` songs of the mood's catalog, one per
|
||||
* artist: a radio seeded by three tracks of the same artist adds nothing.
|
||||
*/
|
||||
internal fun radioSeedIds(
|
||||
collection: List<SongRecord>,
|
||||
source: String,
|
||||
limit: Int,
|
||||
): List<String> = collection.asReversed()
|
||||
.filter { it.source == source }
|
||||
.distinctBy { matchKey(it.artist) }
|
||||
.take(limit)
|
||||
.map { it.externalId }
|
||||
|
||||
/** Distinct albums of the collection, deduplicated loosely. */
|
||||
internal fun albumsOf(collection: List<SongRecord>): List<SeedAlbum> =
|
||||
collection.mapNotNull { song ->
|
||||
@@ -223,6 +241,39 @@ internal fun albumsOf(collection: List<SongRecord>): List<SeedAlbum> =
|
||||
SeedAlbum(album, song.artist)
|
||||
}.distinctBy { "${matchKey(it.title)}|${matchKey(it.artist)}" }
|
||||
|
||||
/**
|
||||
* Keeps one copy per recording. A radio and an album endpoint may return the
|
||||
* same song twice, and two uploads of one song only differ by external id; the
|
||||
* copy with the stronger catalog affinity wins.
|
||||
*/
|
||||
internal fun mergeCandidates(
|
||||
items: Iterable<TrackCandidate>,
|
||||
): LinkedHashMap<String, TrackCandidate> {
|
||||
val byId = LinkedHashMap<String, TrackCandidate>()
|
||||
val idForRecording = HashMap<String, String>()
|
||||
items.forEach { candidate ->
|
||||
val recording = recordingKey(candidate.artist, candidate.title)
|
||||
val currentId = idForRecording[recording]
|
||||
val current = currentId?.let(byId::get)
|
||||
when {
|
||||
current == null -> {
|
||||
byId[candidate.externalId] = candidate
|
||||
idForRecording[recording] = candidate.externalId
|
||||
}
|
||||
candidate.affinity > current.affinity -> {
|
||||
byId.remove(current.externalId)
|
||||
byId[candidate.externalId] = candidate
|
||||
idForRecording[recording] = candidate.externalId
|
||||
}
|
||||
}
|
||||
}
|
||||
return byId
|
||||
}
|
||||
|
||||
/** Identity of a recording, independent of the catalog's track id. */
|
||||
internal fun recordingKey(artist: String, title: String): String =
|
||||
"${matchKey(artist)}|${matchKey(title)}"
|
||||
|
||||
/**
|
||||
* Picks the best [limit] candidates while penalising an artist that keeps
|
||||
* winning: without it, a mood with three songs by one artist would fill every
|
||||
|
||||
Reference in new issue
Block a user