fix(enrichment): official releases outrank unofficial studio albums

_best_release sorted (clean, status_ok, date), so an UNofficial bootleg Album
outranked an official Single/EP/comp — regressing canonical album/year and
seeding cover-art from a bootleg for single-only songs. Order status_ok before
clean: official first, then prefer a clean studio album among the official
releases (still surfaces the studio album over an official live/comp album).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Claude Opus 4.8 (1M context)
2026-07-04 22:59:30 +02:00
parent fc52d1f9d2
commit b083d2dd45
2 changed files with 28 additions and 1 deletions
+5 -1
View File
@@ -283,7 +283,11 @@ def _best_release(doc: dict) -> dict:
clean = 0 if _is_clean_studio_album(rg) else 1
status_ok = 0 if str(r.get("status", "")).lower() == "official" else 1
date = str(r.get("date", "") or "9999")
return (clean, status_ok, date)
# Official FIRST, then prefer a clean studio album: this still surfaces
# the studio album over an (official) live/comp album for the display
# album/year, but never lets an UNofficial bootleg album outrank an
# official single/EP/comp — which `(clean, status_ok, …)` would.
return (status_ok, clean, date)
return sorted(releases, key=sort_key)[0]
+23
View File
@@ -202,6 +202,29 @@ def test_parse_recording_doc_normalizes():
assert c["mb_score"] == 98
def test_best_release_prefers_official_single_over_unofficial_album():
"""An OFFICIAL single/EP must outrank an UNofficial bootleg album for the
canonical album/year: official comes before the studio-album preference, so
a single-only song is never seeded from a bootleg. (`(clean, status_ok, …)`
would wrongly pick the bootleg.)"""
doc = {
"id": "rec-x", "title": "One-Off", "score": 90,
"artist-credit": [
{"name": "A", "joinphrase": "",
"artist": {"id": "a", "name": "A", "sort-name": "A"}}],
"releases": [
{"id": "rel-boot", "title": "Boot LP", "status": "Bootleg",
"date": "1990-01-01", "release-group": {"primary-type": "Album"}},
{"id": "rel-single", "title": "The Single", "status": "Official",
"date": "1988-01-01", "release-group": {"primary-type": "Single"}},
],
}
c = m.parse_recording_doc(doc)
assert c["release_id"] == "rel-single"
assert c["album"] == "The Single"
assert c["studio"] is False # a Single isn't a clean studio ALBUM
def test_parse_recording_doc_joined_artist_credit():
doc = dict(MB_DOC)
doc["artist-credit"] = [