imacat/pop-fem-audit
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity

Remove the retired artist overrides layer and the mixed artist type

Browse Source 
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
imacat
2026-08-04 15:15:49 +08:00
co-authored by Claude Fable 5
parent 93aa06703b
commit 15f207ffc6
8 changed files with 24 additions and 70 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/src/pop_fem_audit_tools/build_db.py
+4 -11
View File
@@ -8,8 +8,8 @@ Rebuilds the working store from scratch out of the committed
inputs: the year-end chart CSV and the output directory for the
review CSV files, given as the two positional command-line
arguments, and the optional capture inputs, each given as an
option: the lyrics cache directory, the Wikidata artist snapshot
CSV, and the manual artist overrides CSV. An omitted option
option: the lyrics cache directory and the Wikidata artist
snapshot CSV. An omitted option
leaves its capture layer unloaded; a given option whose path does
not exist fails the build. Missing tables
are created on a fresh store; existing tables are never altered,
@@ -188,9 +188,6 @@ def parse_args(argv: list[str] | None) -> argparse.Namespace:
parser.add_argument(
"--wikidata-csv", type=Path, default=None,
help="the Wikidata artist snapshot CSV file to apply")
parser.add_argument(
"--overrides-csv", type=Path, default=None,
help="the manual artist override CSV file to apply")
return parser.parse_args(argv)
@@ -215,8 +212,7 @@ def parse_artist_credit(credit: str) -> list[tuple[str, Role]]:
word or punctuation.
Known limitation: a compound act name that contains one of the
delimiters, other than the protected names, is over-split;
such cases are corrected later via the human override layer.
delimiters, other than the protected names, is over-split.
:param credit: The combined artist credit string.
:return: The (name, role) pairs in credit order, primary side
@@ -407,8 +403,7 @@ def apply_artist_csv(session: Session, path: Path) -> None:
"""Apply an artist attribute CSV onto the artist rows.
Artists match by exact name. Only the non-empty cells are
applied, so a later CSV overrides an earlier one field by
field. The note column is ignored.
applied, field by field. The note column is ignored.
:param session: The database session, with the artists
flushed.
@@ -727,8 +722,6 @@ def main(argv: list[str] | None = None) -> int:
load_lyrics(session, args.lyrics_dir)
if args.wikidata_csv is not None:
apply_artist_csv(session, args.wikidata_csv)
if args.overrides_csv is not None:
apply_artist_csv(session, args.overrides_csv)
session.flush()
violations: list[str] = find_violations(
session, YEARS, RANKS_PER_YEAR)
tools/src/pop_fem_audit_tools/fetch_artists.py
-3
View File
@@ -106,9 +106,6 @@ class ArtistType(enum.StrEnum):
"""A solo artist: a human."""
GROUP = "group"
"""A musical ensemble."""
MIXED = "mixed"
"""A mixed act, assigned manually via the overrides; never
derived by the fetcher."""
@dataclass
tools/src/pop_fem_audit_tools/models.py
+1 -1
View File
@@ -78,7 +78,7 @@ class Artist(Base):
gender: Mapped[str | None]
"""The gender of the artist."""
type: Mapped[str | None]
"""The artist type: solo, group, or mixed."""
"""The artist type: solo or group."""
genre: Mapped[str | None]
"""The music genre of the artist."""
country: Mapped[str | None]
tools/tests/test_build_db.py
-50
View File
@@ -258,8 +258,6 @@ class TestBuildDB(unittest.TestCase):
self.__lyrics: Path = self.__dir / "lyrics"
self.__wikidata: Path = \
self.__dir / "artists_wikidata.csv"
self.__overrides: Path = \
self.__dir / "artists_overrides.csv"
self.__write_chart(self.CHART_CSV)
url: str = f"sqlite:///{self.__dir}/store.sqlite3"
config.set_settings(config.Settings(
@@ -573,42 +571,6 @@ class TestBuildDB(unittest.TestCase):
list(session.scalars(sa.select(ChartEntry))), [])
self.assertEqual(list(session.scalars(sa.select(Song))), [])
def test_overrides_apply_over_wikidata(self) -> None:
"""Test that the overrides win over the Wikidata snapshot."""
self.__wikidata.write_text(
"name,qid,gender,type,genre,country,note\n"
"Adele,Q2831,female,solo,pop,GB,\n",
encoding="utf-8")
self.__overrides.write_text(
"name,qid,gender,type,genre,country,note\n"
"Adele,,,,soul,,manually checked\n",
encoding="utf-8")
self.assertEqual(self.__run_build(
"--wikidata-csv", str(self.__wikidata),
"--overrides-csv", str(self.__overrides))[0], 0)
session: Session = self.__session()
artist: Artist | None = session.scalar(
sa.select(Artist).where(Artist.name == "Adele"))
assert artist is not None
self.assertEqual(artist.genre, "soul")
self.assertEqual(artist.gender, "female")
self.assertEqual(artist.wikidata_qid, "Q2831")
self.assertEqual(artist.country, "GB")
def test_unknown_override_name_fails(self) -> None:
"""Test that an unknown override name fails the build."""
self.__overrides.write_text(
"name,qid,gender,type,genre,country,note\n"
"Adel,,female,,,,typo\n", encoding="utf-8")
status: int
stderr: str
status, stderr = self.__run_build(
"--overrides-csv", str(self.__overrides))
self.assertNotEqual(status, 0)
self.assertIn("Adel", stderr)
session: Session = self.__session()
self.assertEqual(list(session.scalars(sa.select(Song))), [])
def test_lyrics_loaded(self) -> None:
"""Test loading the lyrics cache into the songs."""
self.__lyrics.mkdir()
@@ -676,18 +638,6 @@ class TestBuildDB(unittest.TestCase):
session: Session = self.__session()
self.assertEqual(list(session.scalars(sa.select(Song))), [])
def test_missing_overrides_csv_fails(self) -> None:
"""Test that a given but missing override CSV fails."""
status: int
stderr: str
status, stderr = self.__run_build(
"--overrides-csv", str(self.__overrides))
self.assertNotEqual(status, 0)
self.assertIn("error:", stderr)
self.assertIn(str(self.__overrides), stderr)
session: Session = self.__session()
self.assertEqual(list(session.scalars(sa.select(Song))), [])
REVIEW_CHART_CSV: str = (
"year,rank,title,artist\n"
"2016,1,banana,Artist B\n"