refactor: compute coverage once, index proofs

EntryCategories asked every core in turn: 3.8 million proofs for 7,430
entries. ProofIndex looks each key up once, and verify --all --json is
byte-identical (24 s to 17 s). generate_site and generate_readme now share
one coverage, cached in tmp/coverage-cache keyed by its inputs, so the
README step drops from 25 s to 3 s.
This commit is contained in:
Abdessamad Derraz committed 2026-10-22 12:23:26 +02:00
1 parent f67f4ead1b
commit baf38ffbee
6 files changed
+349 -33

No files matched your search

+100
View File
@@ -0,0 +1,100 @@
"""The site and the README share one coverage computation.
generate_site.py and generate_readme.py each verified every platform, a
minute of the site build spent twice on the same answer. The first to run
stores the coverage, keyed by its inputs, and the second reads it. A cache
that outlived a change to its inputs would publish stale counts, so these
tests change an input and expect a fresh computation.
"""
from __future__ import annotations
import sys
import tempfile
import unittest
from pathlib import Path
from unittest import mock
REPO_ROOT = Path(__file__).resolve().parent.parent
sys.path.insert(0, str(REPO_ROOT / "scripts"))
import generate_readme # noqa: E402
class CoverageCache(unittest.TestCase):
def setUp(self) -> None:
self.work = Path(tempfile.mkdtemp(dir=REPO_ROOT / "tmp" / "tests"))
self.platforms = self.work / "platforms"
self.platforms.mkdir()
(self.platforms / "alpha.yml").write_text("platform: Alpha\n")
self.emulators = self.work / "emulators"
self.emulators.mkdir()
self.db = self.work / "database.json"
self.db.write_text("{}")
self.calls: list[str] = []
patches = [
mock.patch.object(generate_readme, "COVERAGE_CACHE_DIR", self.work / "cache"),
mock.patch.object(generate_readme, "compute_coverage", self._compute),
]
for patch in patches:
patch.start()
self.addCleanup(patch.stop)
def tearDown(self) -> None:
import shutil
shutil.rmtree(self.work, ignore_errors=True)
def _compute(self, name, platforms_dir, db, data_registry=None, emulators_dir=""):
self.calls.append(name)
if name == "ghost":
raise FileNotFoundError(name)
return {"platform": name.title(), "missing_names": {"a.bin"}}
def _run(self, names=("beta", "alpha")) -> dict:
return generate_readme.platform_coverages(
list(names), str(self.platforms), {}, {},
emulators_dir=str(self.emulators), db_path=str(self.db),
)
def test_second_run_reads_the_first(self):
first = self._run()
self.assertEqual(self.calls, ["alpha", "beta"])
second = self._run()
self.assertEqual(self.calls, ["alpha", "beta"])
self.assertEqual(first, second)
# The caller's order, not the computation's.
self.assertEqual(list(second), ["beta", "alpha"])
self.assertEqual(second["alpha"]["missing_names"], {"a.bin"})
def test_a_changed_input_computes_again(self):
self._run()
for change in (
lambda: (self.platforms / "alpha.yml").write_text("platform: Alpha 2\n"),
lambda: self.db.write_text('{"files": {}}'),
lambda: (self.emulators / "core.yml").write_text("emulator: core\n"),
):
self.calls.clear()
change()
self._run()
self.assertEqual(self.calls, ["alpha", "beta"])
def test_another_platform_list_computes_again(self):
self._run()
self.calls.clear()
self._run(("alpha",))
self.assertEqual(self.calls, ["alpha"])
def test_a_platform_without_a_file_is_left_out(self):
self.assertEqual(list(self._run(("ghost", "alpha"))), ["alpha"])
self.assertEqual(list(self._run(("ghost", "alpha"))), ["alpha"])
def test_one_cache_file_is_kept(self):
self._run()
(self.platforms / "alpha.yml").write_text("platform: Alpha 3\n")
self._run()
self.assertEqual(len(list((self.work / "cache").glob("*.pickle"))), 1)
if __name__ == "__main__":
unittest.main()