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

Make every subcommand input an explicit CLI argument or option

Browse Source 
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
imacat
2026-08-04 15:13:31 +08:00
co-authored by Claude Fable 5
parent e0eb343ce0
commit e9027472f4
12 changed files with 285 additions and 174 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/tests/test_build_db.py
+85 -22
View File
@@ -4,7 +4,6 @@
# imacat@mail.imacat.idv.tw (imacat), 2026/7/31
"""Unit tests for the working store builder module."""
import io
import os
import tempfile
import unittest
from contextlib import redirect_stderr
@@ -104,15 +103,17 @@ class TestBuildDB(unittest.TestCase):
"""The default chart CSV fixture: 2 years with 2 ranks each."""
def setUp(self) -> None:
"""Create a temporary working directory with the fixtures."""
"""Create a temporary data directory with the fixtures."""
tmp: tempfile.TemporaryDirectory[str] \
= tempfile.TemporaryDirectory()
self.addCleanup(tmp.cleanup)
self.__dir: Path = Path(tmp.name)
old_cwd: str = os.getcwd()
self.addCleanup(os.chdir, old_cwd)
os.chdir(self.__dir)
Path("data").mkdir()
self.__chart: Path = self.__dir / "chart.csv"
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(
@@ -127,26 +128,25 @@ class TestBuildDB(unittest.TestCase):
patcher.start()
self.addCleanup(patcher.stop)
@staticmethod
def __write_chart(content: str) -> None:
def __write_chart(self, content: str) -> None:
"""Write the chart CSV fixture.
:param content: The CSV content.
:return: None.
"""
Path("data/yearend_hot100_2016_2025.csv").write_text(
content, encoding="utf-8")
self.__chart.write_text(content, encoding="utf-8")
@staticmethod
def __run_build() -> tuple[int, str]:
def __run_build(self, *options: str) -> tuple[int, str]:
"""Run the build with the standard error captured.
:param options: The additional command-line options.
:return: A tuple of the exit status and the standard
error.
"""
stderr: io.StringIO = io.StringIO()
with redirect_stderr(stderr):
status: int = build_db.main([])
status: int = build_db.main(
[str(self.__chart), *options])
return status, stderr.getvalue()
def __session(self) -> Session:
@@ -244,15 +244,17 @@ class TestBuildDB(unittest.TestCase):
def test_overrides_apply_over_wikidata(self) -> None:
"""Test that the overrides win over the Wikidata snapshot."""
Path("data/artists_wikidata.csv").write_text(
self.__wikidata.write_text(
"name,qid,gender,type,genre,country,note\n"
"Adele,Q2831,female,solo,pop,GB,\n",
encoding="utf-8")
Path("data/artists_overrides.csv").write_text(
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()[0], 0)
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"))
@@ -264,12 +266,13 @@ class TestBuildDB(unittest.TestCase):
def test_unknown_override_name_fails(self) -> None:
"""Test that an unknown override name fails the build."""
Path("data/artists_overrides.csv").write_text(
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()
status, stderr = self.__run_build(
"--overrides-csv", str(self.__overrides))
self.assertNotEqual(status, 0)
self.assertIn("Adel", stderr)
session: Session = self.__session()
@@ -277,14 +280,15 @@ class TestBuildDB(unittest.TestCase):
def test_lyrics_loaded(self) -> None:
"""Test loading the lyrics cache into the songs."""
Path("data/lyrics").mkdir()
Path("data/lyrics/1.txt").write_text(
self.__lyrics.mkdir()
(self.__lyrics / "1.txt").write_text(
"Hello, it's me\n", encoding="utf-8")
Path("data/lyrics/999.txt").write_text(
(self.__lyrics / "999.txt").write_text(
"orphan\n", encoding="utf-8")
status: int
stderr: str
status, stderr = self.__run_build()
status, stderr = self.__run_build(
"--lyrics-dir", str(self.__lyrics))
self.assertEqual(status, 0)
self.assertIn("999", stderr)
self.assertIn("1 songs with lyrics", stderr)
@@ -293,3 +297,62 @@ class TestBuildDB(unittest.TestCase):
assert song is not None
self.assertEqual(song.title, "Hello")
self.assertEqual(song.lyrics, "Hello, it's me\n")
def test_omitted_options_skip_capture_layers(self) -> None:
"""Test that omitted options leave the layers unloaded."""
self.__lyrics.mkdir()
(self.__lyrics / "1.txt").write_text(
"Hello, it's me\n", encoding="utf-8")
self.__wikidata.write_text(
"name,qid,gender,type,genre,country,note\n"
"Adele,Q2831,female,solo,pop,GB,\n",
encoding="utf-8")
status: int
stderr: str
status, stderr = self.__run_build()
self.assertEqual(status, 0)
self.assertIn("0 songs with lyrics", stderr)
session: Session = self.__session()
song: Song | None = session.get(Song, 1)
assert song is not None
self.assertIsNone(song.lyrics)
artist: Artist | None = session.scalar(
sa.select(Artist).where(Artist.name == "Adele"))
assert artist is not None
self.assertIsNone(artist.wikidata_qid)
self.assertIsNone(artist.gender)
def test_missing_lyrics_dir_fails(self) -> None:
"""Test that a given but missing lyrics directory fails."""
status: int
stderr: str
status, stderr = self.__run_build(
"--lyrics-dir", str(self.__lyrics))
self.assertNotEqual(status, 0)
self.assertIn(f"error: {self.__lyrics}", stderr)
session: Session = self.__session()
self.assertEqual(list(session.scalars(sa.select(Song))), [])
def test_missing_wikidata_csv_fails(self) -> None:
"""Test that a given but missing snapshot CSV fails."""
status: int
stderr: str
status, stderr = self.__run_build(
"--wikidata-csv", str(self.__wikidata))
self.assertNotEqual(status, 0)
self.assertIn("error:", stderr)
self.assertIn(str(self.__wikidata), stderr)
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))), [])
tools/tests/test_fetch_artists.py
+11 -14
View File
@@ -6,7 +6,6 @@
import csv
import io
import json
import os
import tempfile
import unittest
import urllib.error
@@ -31,15 +30,13 @@ class TestFetchArtists(unittest.TestCase):
"""The expected header row of the snapshot CSV file."""
def setUp(self) -> None:
"""Create a temporary working directory with the store."""
"""Create a temporary capture directory with the store."""
tmp: tempfile.TemporaryDirectory[str] \
= tempfile.TemporaryDirectory()
self.addCleanup(tmp.cleanup)
self.__dir: Path = Path(tmp.name)
old_cwd: str = os.getcwd()
self.addCleanup(os.chdir, old_cwd)
os.chdir(self.__dir)
Path("data").mkdir()
self.__snapshot: Path = \
self.__dir / "artists_wikidata.csv"
url: str = f"sqlite:///{self.__dir}/store.sqlite3"
config.set_settings(config.Settings(
SQLALCHEMY_DATABASE_URL=url,
@@ -116,8 +113,7 @@ class TestFetchArtists(unittest.TestCase):
x: {"labels": {"en": {"value": y}}}
for x, y in labels.items()}}
@staticmethod
def __run_fetch() -> tuple[int, str]:
def __run_fetch(self) -> tuple[int, str]:
"""Run the fetcher with the standard error captured.
:return: A tuple of the exit status and the standard
@@ -125,7 +121,8 @@ class TestFetchArtists(unittest.TestCase):
"""
stderr: io.StringIO = io.StringIO()
with redirect_stderr(stderr):
status: int = fetch_artists.main([])
status: int = fetch_artists.main(
[str(self.__snapshot)])
return status, stderr.getvalue()
@staticmethod
@@ -183,7 +180,7 @@ class TestFetchArtists(unittest.TestCase):
"?action=wbgetentities&ids=Q2%7CQ5%7CQ3%7CQ4%7CQ6"
"&props=labels&languages=en&format=json")
rows: list[list[str]] = self.__read_rows(
Path("data/artists_wikidata.csv"))
self.__snapshot)
self.assertEqual(len(rows), 2)
self.assertEqual(rows[0], self.HEADER)
self.assertEqual(rows[1], [
@@ -214,7 +211,7 @@ class TestFetchArtists(unittest.TestCase):
status: int = self.__run_fetch()[0]
self.assertEqual(status, 0)
rows: list[list[str]] = self.__read_rows(
Path("data/artists_wikidata.csv"))
self.__snapshot)
self.assertEqual(len(rows), 2)
self.assertEqual(rows[1], [
"BTS", "Q10", "", "group", "K-pop", "South Korea",
@@ -234,7 +231,7 @@ class TestFetchArtists(unittest.TestCase):
self.assertEqual(status, 0)
self.assertEqual(urlopen.call_count, 1)
rows: list[list[str]] = self.__read_rows(
Path("data/artists_wikidata.csv"))
self.__snapshot)
self.assertEqual(len(rows), 2)
self.assertEqual(rows[0], self.HEADER)
self.assertEqual(rows[1], [
@@ -255,7 +252,7 @@ class TestFetchArtists(unittest.TestCase):
status, stderr = self.__run_fetch()
self.assertEqual(status, 0)
rows: list[list[str]] = self.__read_rows(
Path("data/artists_wikidata.csv"))
self.__snapshot)
self.assertEqual(len(rows), 3)
self.assertEqual(rows[1][:2], ["Broken", ""])
self.assertTrue(rows[1][6].startswith("error: "))
@@ -268,7 +265,7 @@ class TestFetchArtists(unittest.TestCase):
def test_rerun_skips_existing(self) -> None:
"""Test that the snapshot rows are skipped and preserved."""
self.__seed(["Adele", "Nobody"])
snapshot: Path = Path("data/artists_wikidata.csv")
snapshot: Path = self.__snapshot
old_row: list[str] = [
"Adele", "Q1", "female", "solo", "pop",
"United Kingdom", "English singer"]
tools/tests/test_fetch_lyrics.py
+27 -27
View File
@@ -6,7 +6,6 @@
import csv
import io
import json
import os
import tempfile
import unittest
import urllib.error
@@ -38,15 +37,15 @@ class TestFetchLyrics(unittest.TestCase):
"""The expected header row of the missing report CSV file."""
def setUp(self) -> None:
"""Create a temporary working directory with the store."""
"""Create a temporary capture directory with the store."""
tmp: tempfile.TemporaryDirectory[str] \
= tempfile.TemporaryDirectory()
self.addCleanup(tmp.cleanup)
self.__dir: Path = Path(tmp.name)
old_cwd: str = os.getcwd()
self.addCleanup(os.chdir, old_cwd)
os.chdir(self.__dir)
Path("data").mkdir()
self.__lyrics: Path = self.__dir / "lyrics"
self.__provenance: Path = \
self.__dir / "lyrics_provenance.csv"
self.__missing: Path = self.__dir / "lyrics_missing.csv"
url: str = f"sqlite:///{self.__dir}/store.sqlite3"
config.set_settings(config.Settings(
SQLALCHEMY_DATABASE_URL=url,
@@ -110,8 +109,7 @@ class TestFetchLyrics(unittest.TestCase):
return urllib.error.HTTPError(
"https://example.com/", 404, "Not Found", None, None)
@staticmethod
def __run_fetch() -> tuple[int, str]:
def __run_fetch(self) -> tuple[int, str]:
"""Run the fetcher with the standard error captured.
:return: A tuple of the exit status and the standard
@@ -119,7 +117,9 @@ class TestFetchLyrics(unittest.TestCase):
"""
stderr: io.StringIO = io.StringIO()
with redirect_stderr(stderr):
status: int = fetch_lyrics.main([])
status: int = fetch_lyrics.main(
[str(self.__lyrics), str(self.__provenance),
str(self.__missing)])
return status, stderr.getvalue()
@staticmethod
@@ -149,10 +149,11 @@ class TestFetchLyrics(unittest.TestCase):
self.assertEqual(request.get_header("User-agent"),
fetch_lyrics.USER_AGENT)
self.assertEqual(
Path("data/lyrics/1.txt").read_text(encoding="utf-8"),
(self.__lyrics / "1.txt")
.read_text(encoding="utf-8"),
"Hello, it's me\n")
rows: list[list[str]] = self.__read_rows(
Path("data/lyrics_provenance.csv"))
self.__provenance)
self.assertEqual(len(rows), 2)
self.assertEqual(rows[0], self.PROVENANCE_HEADER)
self.assertEqual(rows[1][:3],
@@ -175,10 +176,11 @@ class TestFetchLyrics(unittest.TestCase):
self.assertEqual(status, 0)
self.assertEqual(urlopen.call_count, 2)
self.assertEqual(
Path("data/lyrics/1.txt").read_text(encoding="utf-8"),
(self.__lyrics / "1.txt")
.read_text(encoding="utf-8"),
"Hello\n")
rows: list[list[str]] = self.__read_rows(
Path("data/lyrics_provenance.csv"))
self.__provenance)
self.assertEqual(rows[1][:2], ["1", "lrclib"])
def test_both_miss(self) -> None:
@@ -192,11 +194,9 @@ class TestFetchLyrics(unittest.TestCase):
stderr: str
status, stderr = self.__run_fetch()
self.assertEqual(status, 0)
self.assertFalse(Path("data/lyrics/1.txt").exists())
self.assertFalse(
Path("data/lyrics_provenance.csv").exists())
rows: list[list[str]] = self.__read_rows(
Path("data/lyrics_missing.csv"))
self.assertFalse((self.__lyrics / "1.txt").exists())
self.assertFalse(self.__provenance.exists())
rows: list[list[str]] = self.__read_rows(self.__missing)
self.assertEqual(len(rows), 2)
self.assertEqual(rows[0], self.MISSING_HEADER)
self.assertEqual(rows[1][:3], ["1", "Hello", "Adele"])
@@ -205,8 +205,8 @@ class TestFetchLyrics(unittest.TestCase):
def test_cached_song_skipped(self) -> None:
"""Test that a cached song triggers no HTTP request."""
self.__seed([("Hello", "Adele")])
Path("data/lyrics").mkdir()
Path("data/lyrics/1.txt").write_text(
self.__lyrics.mkdir()
(self.__lyrics / "1.txt").write_text(
"cached\n", encoding="utf-8")
urlopen: mock.Mock
with mock.patch("urllib.request.urlopen") as urlopen:
@@ -214,10 +214,10 @@ class TestFetchLyrics(unittest.TestCase):
self.assertEqual(status, 0)
urlopen.assert_not_called()
self.assertEqual(
Path("data/lyrics/1.txt").read_text(encoding="utf-8"),
(self.__lyrics / "1.txt")
.read_text(encoding="utf-8"),
"cached\n")
rows: list[list[str]] = self.__read_rows(
Path("data/lyrics_missing.csv"))
rows: list[list[str]] = self.__read_rows(self.__missing)
self.assertEqual(rows, [self.MISSING_HEADER])
def test_url_encoding(self) -> None:
@@ -252,17 +252,17 @@ class TestFetchLyrics(unittest.TestCase):
self.__response({"lyrics": "one\n"}),
self.__response({"lyrics": "two\n"})]):
self.assertEqual(self.__run_fetch()[0], 0)
provenance: Path = Path("data/lyrics_provenance.csv")
rows: list[list[str]] = self.__read_rows(provenance)
rows: list[list[str]] = self.__read_rows(
self.__provenance)
self.assertEqual(len(rows), 3)
self.assertEqual(rows[0], self.PROVENANCE_HEADER)
Path("data/lyrics/2.txt").unlink()
(self.__lyrics / "2.txt").unlink()
with mock.patch(
"urllib.request.urlopen",
side_effect=[
self.__response({"lyrics": "two again\n"})]):
self.assertEqual(self.__run_fetch()[0], 0)
rows = self.__read_rows(provenance)
rows = self.__read_rows(self.__provenance)
self.assertEqual(len(rows), 4)
self.assertEqual(rows[0], self.PROVENANCE_HEADER)
self.assertNotIn(self.PROVENANCE_HEADER, rows[1:])
tools/tests/test_run_llm.py
+16 -17
View File
@@ -6,7 +6,6 @@
"""Unit tests for the run_llm batch runner module."""
import io
import json
import os
import tempfile
import unittest
from contextlib import redirect_stderr, redirect_stdout
@@ -310,24 +309,24 @@ class TestMainFlow(RunLLMTestCase):
"""Test cases for the end-to-end main flow."""
def setUp(self) -> None:
"""Create a temporary working directory with input files."""
"""Create a temporary directory with the input files."""
directory: Path = self._make_temp_dir()
old_cwd: str = os.getcwd()
self.addCleanup(os.chdir, old_cwd)
os.chdir(directory)
Path("prompts").mkdir()
Path("prompts/task_v1.md").write_text(
"The task prompt.\n", encoding="utf-8")
Path("prompts/task_arbitration_v1.md").write_text(
self.__runs: Path = directory / "runs"
prompt: Path = directory / "task_v1.md"
prompt.write_text("The task prompt.\n", encoding="utf-8")
arbitration: Path = directory / "task_arbitration_v1.md"
arbitration.write_text(
"The arbitration prompt.\n", encoding="utf-8")
Path("items.jsonl").write_text(
self.__input: Path = directory / "items.jsonl"
self.__input.write_text(
'{"id": "a", "content": "first item"}\n'
'{"id": "b", "content": "second item"}\n',
encoding="utf-8")
self.__argv: list[str] = [
"--prompt", "prompts/task_v1.md",
"--arbitration-prompt", "prompts/task_arbitration_v1.md",
"--input", "items.jsonl",
str(self.__runs),
"--prompt", str(prompt),
"--arbitration-prompt", str(arbitration),
"--input", str(self.__input),
"--phase", "coding"]
self.__settings: config.Settings = config.Settings(
SQLALCHEMY_DATABASE_URL="sqlite://",
@@ -385,7 +384,8 @@ class TestMainFlow(RunLLMTestCase):
:return: The archive directory.
"""
directories: list[Path] = list(Path("runs/coding").iterdir())
directories: list[Path] = list(
(self.__runs / "coding").iterdir())
self.assertEqual(len(directories), 1)
return directories[0]
@@ -509,9 +509,8 @@ class TestMainFlow(RunLLMTestCase):
def test_invalid_input_exits_non_zero(self) -> None:
"""Test that an invalid input file aborts before archiving."""
Path("items.jsonl").write_text(
'{"id": "a"}\n', encoding="utf-8")
self.__input.write_text('{"id": "a"}\n', encoding="utf-8")
status: int = self.__run_main(
self.__argv + ["--dry-run"])[0]
self.assertEqual(status, 1)
self.assertFalse(Path("runs").exists())
self.assertFalse(self.__runs.exists())