refactor: read measurements from the local tree

The site compiles the index and the SQLite files from measurements/
instead of a pinned clone. The pin, the sync script, the CI clone steps,
the freshness area and its refresh handler are gone. core_probe --record
writes into measurements/ of the checkout by default, and a test fails
when a line or data file HEAD holds changed or vanished.
This commit is contained in:
Abdessamad Derraz committed 2026-10-27 09:11:12 +01:00
1 parent 7dca6ae052
commit 571e50f2a8
17 files changed
+699 -881

No files matched your search

+11 -15
View File
@@ -263,9 +263,10 @@ class FakeCoreTests(unittest.TestCase):
self.assertEqual(record["emulator"], "fake")
self.assertEqual(sorted(p.relative_to(record_dir).as_posix()
for p in record_dir.rglob("*") if p.is_file()),
sorted(["records/fake.jsonl", f"data/fake/{self._only_id(record_dir)}.json.gz"]))
line = json.loads((record_dir / "records" / "fake.jsonl").read_text())
blob = (record_dir / "data" / "fake" / f"{line['id']}.json.gz").read_bytes()
sorted(["measurements/fake.jsonl",
f"measurements/data/fake/{self._only_id(record_dir)}.json.gz"]))
line = json.loads((record_dir / "measurements" / "fake.jsonl").read_text())
blob = (record_dir / "measurements" / "data" / "fake" / f"{line['id']}.json.gz").read_bytes()
self.assertEqual(measurement_records.check_line(line), [])
self.assertEqual(measurement_records.check_pair(line, blob), [])
# The line and its sidecar give back the record the run printed.
@@ -281,14 +282,14 @@ class FakeCoreTests(unittest.TestCase):
@staticmethod
def _only_id(record_dir: Path) -> str:
return json.loads((record_dir / "records" / "fake.jsonl").read_text())["id"]
return json.loads((record_dir / "measurements" / "fake.jsonl").read_text())["id"]
def test_second_run_is_appended_beside_the_first(self) -> None:
record_dir = self.tmp / "appended"
argv = ["run", "--core", str(self.core), "--frames", "1", "--no-trace", "--max-load", "1000",
"--record", str(record_dir), "--subject", "smoke"]
self.assertEqual(self.probe(argv)[0], 0)
lines = record_dir / "records" / "fake.jsonl"
lines = record_dir / "measurements" / "fake.jsonl"
first = lines.read_text()
code, record = self.probe(argv)
self.assertEqual(code, 0)
@@ -301,16 +302,11 @@ class FakeCoreTests(unittest.TestCase):
self.assertEqual(code, 2)
self.assertEqual(len(lines.read_text().splitlines()), 3)
def test_recording_inside_the_tracked_tree_is_refused(self) -> None:
inside = REPO_ROOT / "measurements"
err = io.StringIO()
with contextlib.redirect_stdout(io.StringIO()), contextlib.redirect_stderr(err):
code = core_probe.main(["run", "--core", str(self.core), "--frames", "1", "--no-trace",
"--record", str(inside), "--work-dir", str(self.tmp / "work")])
self.assertEqual(code, 2)
self.assertIn("inside the tracked tree", err.getvalue())
self.assertIn(".cache/measurements", err.getvalue())
self.assertFalse(inside.exists())
def test_record_defaults_to_this_checkout(self) -> None:
parser = core_probe.build_parser()
args = parser.parse_args(["run", "--core", sys.executable, "--record", "--frames", "1"])
self.assertEqual(Path(args.record), REPO_ROOT)
self.assertIsNone(parser.parse_args(["run", "--core", sys.executable]).record)
def test_bench_stats(self) -> None:
code, record = self.probe(["bench", "--core", str(self.core), "--frames", "2", "--warmup", "1",
+160 -117
View File
@@ -1,16 +1,15 @@
"""Core probe records in their own repository, and what the site makes of them.
"""Core probe records under measurements/, and what the site makes of them.
A synthetic measurements repository is built with git under tmp/tests:
records split into a line and a sidecar, read at a pinned commit, compiled
into the index and the SQLite files. The append-only rule is checked the
way --fetch applies it, and two branches that each add a line merge.
Synthetic record trees are built under tmp/tests: records split into a line
and a sidecar, read from the tree, compiled into the index and the SQLite
files. The append-only rule is checked against a commit, two branches that
each add a line merge, and the records this repository holds are checked
against HEAD.
"""
from __future__ import annotations
import contextlib
import copy
import io
import json
import os
import re
@@ -26,10 +25,10 @@ REPO_ROOT = Path(__file__).resolve().parent.parent
sys.path.insert(0, str(REPO_ROOT / "scripts"))
import measurement_records as mr # noqa: E402
import sitemeasurements # noqa: E402
import sync_measurements as sm # noqa: E402
import sitemeasurements as sm # noqa: E402
REPO_URL = "https://github.com/Abdess/retrobios-measurements"
REPO_URL = "https://github.com/Abdess/retrobios"
COMMIT = "e" * 40
SHA1 = "a" * 40
SHA256 = "b" * 64
@@ -95,6 +94,8 @@ def full_record(emulator: str, subject: str, when: str, kind: str = "check",
return record
def git(cwd: Path, *args: str) -> str:
env = {**os.environ, "GIT_AUTHOR_NAME": "t", "GIT_AUTHOR_EMAIL": "t@t", "GIT_COMMITTER_NAME": "t",
"GIT_COMMITTER_EMAIL": "t@t", "GIT_CEILING_DIRECTORIES": str(cwd.parent)}
@@ -122,32 +123,33 @@ def commit_all(tree: Path, message: str) -> str:
class Workspace(unittest.TestCase):
"""A measurements repository with three records and a pin on it."""
"""A tree with three records under measurements/ and one profile."""
def setUp(self) -> None:
(REPO_ROOT / "tmp" / "tests").mkdir(parents=True, exist_ok=True)
self.tmp = Path(tempfile.mkdtemp(dir=REPO_ROOT / "tmp" / "tests"))
self.addCleanup(shutil.rmtree, self.tmp, True)
self.repo = self.tmp / "remote"
self.repo.mkdir()
git(self.repo, "init", "-q", "-b", "main")
(self.repo / ".gitattributes").write_text("records/*.jsonl merge=union\n")
self.first = add_record(self.repo, full_record("alpha", "card", "2026-10-01T10:00:00+00:00"))
self.bench = add_record(self.repo, full_record("alpha", "speed", "2026-10-01T11:00:00+00:00",
self.tree = self.tmp / "tree"
self.tree.mkdir()
self.first = add_record(self.tree, full_record("alpha", "card", "2026-10-01T10:00:00+00:00"))
self.bench = add_record(self.tree, full_record("alpha", "speed", "2026-10-01T11:00:00+00:00",
kind="bench"))
self.beta = add_record(self.repo, full_record("beta", "card", "2026-10-02T10:00:00+00:00",
self.beta = add_record(self.tree, full_record("beta", "card", "2026-10-02T10:00:00+00:00",
values=("1" * 40, "1" * 40)))
self.commit = commit_all(self.repo, "feat: first records")
self.pin = self.tmp / "pin.json"
sm.write_pin({"repo": str(self.repo), "commit": self.commit}, self.pin)
self.emulators = self.tmp / "emulators"
self.emulators.mkdir()
(self.emulators / "alpha.yml").write_text(
'emulator: "Alpha"\ntype: libretro\nsystems:\n - sega-saturn\nfiles: []\n')
def built(self, public: Path, clone: Path | None = None) -> sm.Built:
return sm.build(public, clone or self.repo, self.pin, self.emulators, require=True,
scratch=self.tmp / "scratch", system_names={"sega-saturn": "Sega Saturn"})
def built(self, public: Path) -> sm.Built:
return sm.build(public, self.tree, self.emulators, scratch=self.tmp / "scratch",
system_names={"sega-saturn": "Sega Saturn"}, repo=REPO_URL, commit=COMMIT)
def repository(self) -> str:
"""Make the tree a git repository, its records committed on main."""
git(self.tree, "init", "-q", "-b", "main")
(self.tree / ".gitattributes").write_text("measurements/*.jsonl merge=union\n")
return commit_all(self.tree, "feat: first records")
class RecordSplit(unittest.TestCase):
@@ -211,17 +213,29 @@ class RecordSplit(unittest.TestCase):
self.assertTrue(mr.check_pair(forged, blob))
class SyncAndIndex(Workspace):
def test_records_are_read_at_the_pin_not_the_working_tree(self) -> None:
add_record(self.repo, full_record("alpha", "card", "2026-10-03T10:00:00+00:00"))
records = sm.read_records(self.repo, self.commit)
self.assertEqual(len(records), 3)
class ReadAndIndex(Workspace):
def test_records_are_read_from_the_tree(self) -> None:
records = mr.read_records(self.tree)
self.assertEqual([(s.emulator, s.line) for s in records], [("alpha", 1), ("alpha", 2), ("beta", 1)])
self.assertEqual(mr.read_records(self.tmp / "empty"), [])
def test_a_broken_tree_is_named(self) -> None:
stray = self.tree / mr.DATA_DIR / "beta" / "2026-10-02-000000000000.json.gz"
stray.write_bytes(b"x")
(self.tree / mr.sidecar_path("alpha", self.bench["id"])).unlink()
with self.assertRaises(mr.MeasurementsError) as caught:
mr.read_records(self.tree)
message = str(caught.exception)
self.assertIn(f"{mr.sidecar_path('alpha', self.bench['id'])} is missing", message)
self.assertIn(f"{mr.DATA_DIR}/beta/2026-10-02-000000000000.json.gz: no record line names it", message)
def test_index_shape(self) -> None:
index = self.built(self.tmp / "public").index
self.assertEqual({k: index[k] for k in ("schema_version", "kind", "repo", "commit", "records", "count")},
{"schema_version": 1, "kind": "measurements", "repo": str(self.repo),
"commit": self.commit, "records": 3, "count": 3})
{"schema_version": 1, "kind": "measurements", "repo": REPO_URL,
"commit": COMMIT, "records": 3, "count": 3})
keys = {"emulator", "emulator_name", "profiled", "systems", "system_names", "subject", "kind",
"claim", "method", "observable", "variable", "status", "statement", "content",
"variants", "repetitions", "flags", "date", "host", "core", "frontend_commit", "id",
@@ -232,18 +246,28 @@ class SyncAndIndex(Workspace):
self.assertEqual(alpha["card"]["status"], "differs")
self.assertEqual(alpha["card"]["system_names"], ["Sega Saturn"])
self.assertEqual(alpha["card"]["record_url"],
f"{self.repo}/blob/{self.commit}/records/alpha.jsonl#L1")
f"{REPO_URL}/blob/{COMMIT}/measurements/alpha.jsonl#L1")
self.assertEqual(alpha["card"]["data_url"],
f"{REPO_URL}/blob/{COMMIT}/measurements/data/alpha/{self.first['id']}.json.gz")
self.assertEqual(alpha["speed"]["status"], "measured")
self.assertIn("ms per frame", alpha["speed"]["statement"])
self.assertIn("Test CPU", alpha["speed"]["host"])
written = json.loads((self.tmp / "public" / sm.INDEX_PATH).read_text())
self.assertEqual(written, index)
def test_links_name_the_last_commit_that_touched_the_records(self) -> None:
first = self.repository()
(self.tree / "other.txt").write_text("x")
commit_all(self.tree, "chore: unrelated")
self.assertEqual(mr.last_commit(self.tree), first)
index = sm.build(self.tmp / "public", self.tree, self.emulators, scratch=self.tmp / "scratch").index
self.assertEqual(index["commit"], first)
self.assertTrue(all(f"/blob/{first}/measurements/" in i["record_url"] for i in index["items"]))
def test_latest_record_of_a_subject_wins_and_a_superseded_one_is_dropped(self) -> None:
later = full_record("alpha", "card", "2026-10-05T10:00:00+00:00", values=("3" * 40, "3" * 40))
later["supersedes"] = self.first["id"]
add_record(self.repo, later)
sm.write_pin({"repo": str(self.repo), "commit": commit_all(self.repo, "feat: rerun")}, self.pin)
add_record(self.tree, later)
card = next(i for i in self.built(self.tmp / "public").index["items"]
if i["emulator"] == "alpha" and i["subject"] == "card")
self.assertEqual((card["status"], card["runs"]), ("same", 1))
@@ -257,7 +281,7 @@ class SyncAndIndex(Workspace):
"SELECT name FROM sqlite_master WHERE type = 'table' ORDER BY rowid")]
self.assertEqual(tuple(tables), sm.TABLES)
count = lambda table: connection.execute(f"SELECT COUNT(*) FROM {table}").fetchone()[0] # noqa: E731
records = [s.record for s in sm.read_records(self.repo, self.commit)]
records = [s.record for s in mr.read_records(self.tree)]
self.assertEqual(count("runs"), len(records))
self.assertEqual(count("checks"), sum(1 for r in records if r.get("check")))
self.assertEqual(count("benchmarks"), 2 * sum(1 for r in records if r.get("timing")))
@@ -266,10 +290,12 @@ class SyncAndIndex(Workspace):
sum(len(r["check"]["result"]["groups"]) for r in records if r.get("check")))
self.assertEqual(count("hosts"), 1)
self.assertEqual(count("cores"), 1)
self.assertEqual(dict(connection.execute("SELECT key, value FROM meta"))["measurements_commit"],
self.commit)
meta = dict(connection.execute("SELECT key, value FROM meta"))
self.assertEqual((meta["measurements_repo"], meta["measurements_commit"]), (REPO_URL, COMMIT))
self.assertEqual(connection.execute("SELECT system FROM emulator_systems").fetchall(),
[("sega-saturn",)])
self.assertEqual(connection.execute("SELECT record_url FROM runs WHERE line = 1 AND emulator = 'beta'")
.fetchone()[0], f"{REPO_URL}/blob/{COMMIT}/measurements/beta.jsonl#L1")
indexes = {row[0] for row in connection.execute("SELECT name FROM sqlite_master WHERE type = 'index'")}
self.assertTrue({"runs_emulator_idx", "emulator_systems_system_idx", "checks_claim_idx"} <= indexes)
connection.close()
@@ -286,15 +312,11 @@ class SyncAndIndex(Workspace):
for path in first.paths:
self.assertEqual(path.read_bytes(), (two / path.relative_to(one)).read_bytes(), path.name)
def test_a_missing_pin_fails_only_when_required(self) -> None:
sm.write_pin({"repo": str(self.repo), "commit": "f" * 40}, self.pin)
with self.assertRaises(sm.MeasurementsError):
self.built(self.tmp / "public")
with contextlib.redirect_stderr(io.StringIO()) as err:
built = sm.build(self.tmp / "public", self.repo, self.pin, self.emulators, require=False,
scratch=self.tmp / "scratch")
self.assertIn("WARNING", err.getvalue())
self.assertEqual((built.index["count"], built.index["commit"]), (0, None))
def test_no_records_writes_an_empty_index(self) -> None:
shutil.rmtree(self.tree / mr.RECORDS_DIR)
built = self.built(self.tmp / "public")
self.assertEqual((built.index["records"], built.index["count"]), (0, 0))
self.assertEqual(len(built.paths), 2)
def test_every_line_validates_against_the_schema(self) -> None:
try:
@@ -303,68 +325,82 @@ class SyncAndIndex(Workspace):
self.skipTest("jsonschema is not installed")
import validate_schemas # noqa: PLC0415
self.assertEqual(validate_schemas._measurement_errors(self.repo, self.pin), [])
lines = self.repo / mr.records_path("beta")
self.assertEqual(validate_schemas._measurement_errors(self.tree), [])
lines = self.tree / mr.records_path("beta")
record = json.loads(lines.read_text())
record["kind"] = "guess"
lines.write_text(mr.line_text(record) + "\n")
sm.write_pin({"repo": str(self.repo), "commit": commit_all(self.repo, "bad")}, self.pin)
errors = validate_schemas._measurement_errors(self.repo, self.pin)
self.assertTrue(any("records/beta.jsonl:1" in e and "kind" in e for e in errors), errors)
errors = validate_schemas._measurement_errors(self.tree)
self.assertTrue(any("measurements/beta.jsonl:1" in e and "kind" in e for e in errors), errors)
self.assertIsNotNone(Draft202012Validator)
class AppendOnly(Workspace):
def fetch(self, *extra: str) -> tuple[int, str]:
err = io.StringIO()
with contextlib.redirect_stdout(io.StringIO()), contextlib.redirect_stderr(err):
code = sm.main(["--fetch", "--clone", str(self.tmp / "clone"), "--pin", str(self.pin), *extra])
return code, err.getvalue()
def setUp(self) -> None:
super().setUp()
self.commit = self.repository()
def test_an_appended_line_moves_the_pin(self) -> None:
self.assertEqual(self.fetch()[0], 0)
add_record(self.repo, full_record("alpha", "card", "2026-10-04T10:00:00+00:00"))
head = commit_all(self.repo, "feat: rerun")
self.assertEqual(self.fetch("--bump")[0], 0)
self.assertEqual(sm.load_pin(self.pin)["commit"], head)
def test_an_appended_line_and_a_new_file_pass(self) -> None:
add_record(self.tree, full_record("alpha", "card", "2026-10-04T10:00:00+00:00"))
add_record(self.tree, full_record("gamma", "card", "2026-10-04T10:00:00+00:00"))
self.assertEqual(mr.append_only_problems(self.tree, "HEAD"), [])
def test_a_changed_line_is_refused(self) -> None:
lines = self.repo / mr.records_path("alpha")
def test_a_changed_line_is_named(self) -> None:
lines = self.tree / mr.records_path("alpha")
text = lines.read_text().splitlines()
text[0] = text[0].replace('"Each card, twice."', '"Each card, once."')
lines.write_text("\n".join(text) + "\n")
commit_all(self.repo, "rewrite")
code, err = self.fetch("--bump")
self.assertEqual(code, 1)
self.assertIn("records/alpha.jsonl: line 1 changed", err)
self.assertEqual(sm.load_pin(self.pin)["commit"], self.commit)
self.assertEqual(mr.append_only_problems(self.tree, "HEAD"),
["measurements/alpha.jsonl: line 1 changed"])
def test_a_removed_line_or_data_file_is_refused(self) -> None:
lines = self.repo / mr.records_path("alpha")
def test_a_removed_line_or_data_file_is_named(self) -> None:
lines = self.tree / mr.records_path("alpha")
lines.write_text(lines.read_text().splitlines()[0] + "\n")
(self.repo / mr.sidecar_path("beta", self.beta["id"])).unlink()
commit_all(self.repo, "remove")
code, err = self.fetch()
self.assertEqual(code, 1)
self.assertIn("records/alpha.jsonl: line 2 removed", err)
self.assertIn(f"{mr.sidecar_path('beta', self.beta['id'])}: removed", err)
(self.tree / mr.sidecar_path("beta", self.beta["id"])).unlink()
problems = mr.append_only_problems(self.tree, "HEAD")
self.assertIn("measurements/alpha.jsonl: line 2 removed", problems)
self.assertIn(f"{mr.sidecar_path('beta', self.beta['id'])}: removed", problems)
def test_a_rewritten_data_file_is_named(self) -> None:
data = self.tree / mr.sidecar_path("beta", self.beta["id"])
data.write_bytes(data.read_bytes() + b"x")
self.assertEqual(mr.append_only_problems(self.tree, "HEAD"),
[f"{mr.sidecar_path('beta', self.beta['id'])}: rewritten"])
def test_two_branches_adding_a_line_merge_cleanly(self) -> None:
git(self.repo, "checkout", "-q", "-b", "left")
add_record(self.repo, full_record("alpha", "card", "2026-10-06T10:00:00+00:00"))
commit_all(self.repo, "left")
git(self.repo, "checkout", "-q", "main")
git(self.repo, "checkout", "-q", "-b", "right")
add_record(self.repo, full_record("alpha", "speed", "2026-10-06T11:00:00+00:00", kind="bench",
git(self.tree, "checkout", "-q", "-b", "left")
add_record(self.tree, full_record("alpha", "card", "2026-10-06T10:00:00+00:00"))
commit_all(self.tree, "left")
git(self.tree, "checkout", "-q", "main")
git(self.tree, "checkout", "-q", "-b", "right")
add_record(self.tree, full_record("alpha", "speed", "2026-10-06T11:00:00+00:00", kind="bench",
values=("4" * 40,)))
commit_all(self.repo, "right")
git(self.repo, "merge", "-q", "--no-edit", "left")
merged = git(self.repo, "rev-parse", "HEAD")
self.assertEqual(sm.append_only_problems(self.repo, self.commit, merged), [])
records = sm.read_records(self.repo, merged)
commit_all(self.tree, "right")
git(self.tree, "merge", "-q", "--no-edit", "left")
self.assertEqual(mr.append_only_problems(self.tree, self.commit), [])
records = mr.read_records(self.tree)
self.assertEqual(sum(1 for s in records if s.emulator == "alpha"), 4)
class CommittedRecords(unittest.TestCase):
"""The records this repository holds."""
def test_no_line_or_data_file_changed_or_vanished_since_head(self) -> None:
if subprocess.run(["git", "-C", str(REPO_ROOT), "rev-parse", "--verify", "-q", "HEAD"],
capture_output=True, check=False).returncode != 0:
self.skipTest("not a git checkout")
self.assertEqual(mr.append_only_problems(REPO_ROOT, "HEAD"), [])
def test_every_record_reads_and_joins_its_data(self) -> None:
records = mr.read_records(REPO_ROOT)
self.assertGreaterEqual(len(records), 7)
def test_jsonl_files_merge_by_union(self) -> None:
rules = (REPO_ROOT / ".gitattributes").read_text().splitlines()
rule = next(line for line in rules if line.startswith(f"{mr.RECORDS_DIR}/*.jsonl "))
self.assertIn("merge=union", rule.split())
class SitePages(unittest.TestCase):
ITEM = {
"emulator": "beetle_saturn", "emulator_name": "Beetle Saturn", "profiled": True,
@@ -376,14 +412,14 @@ class SitePages(unittest.TestCase):
"host": "Test CPU, 12 CPUs", "core": {"library": "Beetle Saturn v1.32.1", "commit": "2ce77e2" * 5 + "abcde",
"file": "x.so", "sha256": SHA256, "repo": None, "build": "make"},
"frontend_commit": None, "id": "2026-10-27-43527b763ace", "runs": 2,
"record_url": f"{REPO_URL}/blob/{'e' * 40}/records/beetle_saturn.jsonl#L4",
"data_url": f"{REPO_URL}/blob/{'e' * 40}/data/beetle_saturn/2026-10-27-43527b763ace.json.gz",
"record_url": f"{REPO_URL}/blob/{'e' * 40}/measurements/beetle_saturn.jsonl#L4",
"data_url": f"{REPO_URL}/blob/{'e' * 40}/measurements/data/beetle_saturn/2026-10-27-43527b763ace.json.gz",
"sqlite": "downloads/measurements/beetle_saturn.sqlite",
}
def test_tested_block(self) -> None:
self.assertEqual(sitemeasurements.tested_section("beetle_saturn", []), [])
text = "\n".join(sitemeasurements.tested_section("beetle_saturn", [self.ITEM]))
self.assertEqual(sm.tested_section("beetle_saturn", []), [])
text = "\n".join(sm.tested_section("beetle_saturn", [self.ITEM]))
self.assertTrue(text.startswith("## Tested\n"))
for expected in ("**Result:** `same`", "**Method:** Twice per card. Every input fixed.", "**Ran on:** Test CPU, 12 CPUs",
self.ITEM["record_url"], self.ITEM["data_url"], "1 flag raised", "2 runs",
@@ -392,10 +428,10 @@ class SitePages(unittest.TestCase):
self.assertIn(expected, text)
def test_hosts_table_on_the_method_page(self) -> None:
page = sitemeasurements.with_hosts(f"x\n\n{sitemeasurements.HOSTS_MARKER}\n",
page = sm.with_hosts(f"x\n\n{sm.HOSTS_MARKER}\n",
{"items": [self.ITEM, {**self.ITEM, "host": "Test CPU, 12 CPUs, load 1 before, 2 after"}]})
self.assertIn("| Test CPU, 12 CPUs | 2 |", page)
self.assertNotIn(sitemeasurements.HOSTS_MARKER, page)
self.assertNotIn(sm.HOSTS_MARKER, page)
def test_the_explorer_reads_the_index(self) -> None:
source = (REPO_ROOT / "website" / "src" / "components" / "MeasurementsExplorer.astro").read_text()
@@ -404,37 +440,44 @@ class SitePages(unittest.TestCase):
read = set(re.findall(r"\b(?:item|i)\.([a-z_]+)", source)) - {"length"}
self.assertTrue(read)
self.assertLessEqual(read, set(self.ITEM), read - set(self.ITEM))
page = sitemeasurements.generate_explorer_page({"records": 7, "count": 7, "commit": "e" * 40,
page = sm.generate_explorer_page({"records": 7, "count": 7, "commit": "e" * 40,
"repo": REPO_URL})
self.assertIn("<MeasurementsExplorer />", page)
self.assertIn("downloads/measurements.sqlite", page)
self.assertIn(f"({REPO_URL}/tree/{'e' * 40}/measurements)", page)
def test_the_deploy_clones_the_measurements_at_the_pin(self) -> None:
workflow = (REPO_ROOT / ".github" / "workflows" / "deploy-site.yml").read_text()
clone = workflow.index("Clone the measurements at their pin")
step = workflow[clone:workflow.index("- name:", clone)]
self.assertIn("measurements-pin.json", step)
self.assertIn('fetch -q --depth 1 "$repo" "$commit"', step)
self.assertIn('checkout -q --detach "$commit"', step)
self.assertNotIn("uses:", step)
self.assertLess(clone, workflow.index("Validate data contracts"))
self.assertLess(clone, workflow.index("python scripts/generate_site.py --require-measurements"))
self.assertIn('- "measurements-pin.json"', workflow)
pin = sm.load_pin()
self.assertEqual(pin["repo"], REPO_URL)
def test_the_builds_read_the_records_in_this_repository(self) -> None:
for name in ("deploy-site.yml", "validate.yml"):
workflow = (REPO_ROOT / ".github" / "workflows" / name).read_text()
with self.subTest(workflow=name):
self.assertIn('- "measurements/**"', workflow)
self.assertNotIn("measurements-pin", workflow)
self.assertNotIn(".cache/measurements", workflow)
self.assertNotIn("--require-measurements", workflow)
self.assertFalse((REPO_ROOT / "measurements-pin.json").exists())
self.assertFalse((REPO_ROOT / "scripts" / "sync_measurements.py").exists())
def test_nothing_links_the_former_measurements_repository(self) -> None:
former = "retrobios-" + "measurements"
roots = ["wiki", "schemas", "scripts", "website/src", ".github", "tests", "measurements"]
suffixes = {".md", ".py", ".json", ".jsonl", ".yml", ".astro", ".ts", ".mjs"}
stray = [path.relative_to(REPO_ROOT).as_posix()
for root in roots for path in sorted((REPO_ROOT / root).rglob("*"))
if path.is_file() and path.suffix in suffixes
and former in path.read_text(encoding="utf-8", errors="replace")]
stray += [name for name in ("README.md", "CONTRIBUTING.md")
if former in (REPO_ROOT / name).read_text(encoding="utf-8")]
self.assertEqual(stray, [])
class Freshness(unittest.TestCase):
def test_pin_against_the_remote_head(self) -> None:
import check_freshness as cf # noqa: PLC0415
def test_no_measurements_area(self) -> None:
import check_freshness # noqa: PLC0415
import refresh_stale # noqa: PLC0415
pin = sm.load_pin()
self.assertEqual(cf.check_measurements(False, head=lambda _repo: pin["commit"]).status, cf.OK)
stale = cf.check_measurements(False, head=lambda _repo: "f" * 40)
self.assertEqual(stale.status, cf.STALE)
self.assertIn("sync_measurements.py --fetch --bump", stale.detail)
self.assertEqual(cf.check_measurements(True).status, cf.SKIPPED)
self.assertIn("measurements", cf.AREAS)
self.assertNotIn("measurements", check_freshness.AREAS)
self.assertNotIn("measurements", refresh_stale.AUTO_AREAS)
if __name__ == "__main__":
+10 -19
View File
@@ -248,32 +248,23 @@ class SourceLinksOnlyWhereTheFileIs(unittest.TestCase):
def test_every_rendered_link_is_recorded(self):
record = json.loads(sitesources.SOURCE_PATHS.read_text(encoding="utf-8"))
pages = sorted(_built(DOCS / "emulators").rglob("*.md*")) + sorted(DOCS.glob("gaps*.md*"))
import sync_measurements # noqa: PLC0415
import measurement_records # noqa: PLC0415
# A Tested block links the measurements repository at its pin. The
# record of source trees does not cover it: those paths are checked
# against the pinned tree of the clone itself.
measured_slug = urllib.parse.urlsplit(sync_measurements.load_pin()["repo"]).path.strip("/")
measured: dict[str, set[str]] = {}
# A Tested block links a record line and its data file in this
# repository. The records are append-only, so a file a permalink
# names is still in the tree.
records = set(measurement_records.tree_files(REPO_ROOT))
checked, stray = 0, []
for page in pages:
for found in _PERMALINK.finditer(page.read_text(encoding="utf-8")):
if "/Abdess/retrobios/" in found[0]:
continue
key = f"{found['host']}/{found['slug']}@{found['pin']}"
path = urllib.parse.unquote(found["path"])
checked += 1
if found["slug"] == measured_slug:
if found["pin"] not in measured:
if not sync_measurements.has_commit(sync_measurements.CLONE, found["pin"]):
stray.append((page.name, key, "pin not in the measurements clone"))
measured[found["pin"]] = set()
continue
measured[found["pin"]] = set(
sync_measurements.tree_files(sync_measurements.CLONE, found["pin"]))
if path not in measured[found["pin"]]:
if "/Abdess/retrobios/" in found[0]:
if path.startswith(f"{measurement_records.RECORDS_DIR}/") and path not in records:
stray.append((page.name, key, path))
elif path not in record.get(key, ()):
continue
checked += 1
if path not in record.get(key, ()):
stray.append((page.name, key, path))
self.assertGreater(checked, 1000)
self.assertEqual(stray[:20], [])