fix: immutable=1 probe URI (no sidecar creation guaranteed), fs work inside executor job, WAL-header corruption test case

- probe URI adds immutable=1: SQLite's documented guarantee that the
  read-only connection performs no writes and creates no -wal/-shm
  sidecars, even against a WAL-header database
- exists/stat/resolve and URI construction moved inside the executor
  job with the probe (no event-loop disk I/O)
- new WAL-header corruption test asserts byte-identical file and no
  -shm creation from the probe
This commit is contained in:
Joshua King
2026-09-14 08:45:48 -04:00
parent 5b5aa7c789
commit c3e7c0d3d6
2 changed files with 51 additions and 11 deletions
+19 -11
View File
@@ -66,19 +66,27 @@ async def _preflight_existing_file(
that rewrites the header byte 18/19 and can create -wal/-shm
sidecars — which would modify a corrupt file before detection and
break the leave-untouched guarantee. This preflight therefore
validates the WHOLE file with a READ-ONLY connection (mode=ro URI,
PRAGMA integrity_check, run on the executor like every other DB
call): corruption anywhere fails there, before anything is
written. Missing/empty files skip the preflight (they are created
fresh by the real open).
validates the WHOLE file with a READ-ONLY connection (mode=ro +
immutable=1 URI, PRAGMA integrity_check, run on the executor like
every other DB call): corruption anywhere fails there, before
anything is written. ``immutable=1`` is SQLite's documented
guarantee that the connection performs NO writes and creates NO
sidecars — even a WAL-header file gets its -wal/-shm reads served
without creating the shared-memory file. Missing/empty files skip
the preflight (they are created fresh by the real open). All
filesystem stat/URI work runs inside the executor job with the
probe so the event loop never touches disk.
"""
if not db_path.exists() or db_path.stat().st_size == 0:
return
# Properly escape the path: '#'/'?'/'%' in a directory or file name
# would otherwise be parsed as URI fragments/parameters/escapes.
uri = db_path.resolve().as_uri() + "?mode=ro"
def _probe() -> None:
# The file-state check and URI construction live inside the
# executor job: exists/stat/resolve are disk I/O.
if not db_path.exists() or db_path.stat().st_size == 0:
return
# Properly escape the path: '#'/'?'/'%' in a directory or file
# name would otherwise be parsed as URI fragments/parameters/
# escapes. immutable=1: SQLite guarantees no writes and no
# sidecar creation from this connection.
uri = db_path.resolve().as_uri() + "?mode=ro&immutable=1"
conn = sqlite3.connect(uri, uri=True)
try:
row = conn.execute("PRAGMA integrity_check").fetchone()
+32
View File
@@ -250,6 +250,38 @@ def test_migration_stage_corruption_leaves_db_and_sidecars_untouched(
assert not (tmp_path / "nestquest.db-shm").exists()
def test_wal_mode_corruption_leaves_file_and_sidecars_untouched(
tmp_path, monkeypatch
) -> None:
"""A corrupt WAL-HEADER file must be rejected without creating
-shm sidecars from the read-only preflight itself.
The immutable=1 probe URI is what guarantees a read-only
connection creates no sidecars even for a WAL-header database; the
sidecar assertions after the call prove it.
"""
db_path = tmp_path / "nestquest.db"
# WAL fixture: created via the wrapper (journal_mode=WAL persists).
_valid_database(db_path)
data = bytearray(db_path.read_bytes())
# Corrupt the WAL header flag region: bytes 18/19 hold the
# read/write version numbers (2 = WAL). Flip them to garbage so
# the file claims a broken journal mode.
assert len(data) > 64
data[18] = 0x99
data[19] = 0x99
db_path.write_bytes(bytes(data))
corrupt_bytes = db_path.read_bytes()
digest = hashlib.sha256(corrupt_bytes).hexdigest()
with pytest.raises(ConfigEntryNotReady):
_run(_async_open_database(_make_hass_mock(), db_path))
# Main file byte-identical; no -shm appeared from the probe.
assert hashlib.sha256(db_path.read_bytes()).hexdigest() == digest
assert not (tmp_path / "nestquest.db-shm").exists()
def test_open_failure_closes_connection_when_opened(
tmp_path, monkeypatch
) -> None: