Files
docker-volume-backup/src/baudolo/restore/db/postgres.py
Kevin Veen-Birkenbach efcfe88e7f style!: adopt the core lint bar and migrate to it
The package carried no ruff configuration at all, so it ran on the defaults (E4+E7+E9+F) while infinito-nexus-core, its only consumer, holds itself to a far wider selection. Measured against that selection this tree had 224 findings. It now has none.

The selector list is core's verbatim so both repositories answer to one bar. target-version stays py39 rather than core's py311, because requires-python still declares >=3.9 and pyupgrade would otherwise propose syntax the declared minimum cannot run. Every ignore carries its reason: S603/S607 in particular, since running docker and dump binaries from PATH in list form is this tool's whole job and is already injection-safe.

Two conversions are judgement rather than mechanics. os.path.join(dir, '') was the rsync idiom for a trailing separator, which Path drops, so it becomes an explicit os.sep. os.path.abspath stays where Path.resolve() would follow symlinks and let a symlinked volume test as inside the snapshot subject.

BREAKING CHANGE: VersionMismatch is renamed VersionMismatchError.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-18 01:51:18 +02:00

104 lines
3.0 KiB
Python

from __future__ import annotations
import tempfile
from pathlib import Path
from typing import TYPE_CHECKING
from baudolo.restore.run import docker_exec
from .version import guard
if TYPE_CHECKING:
from collections.abc import Iterable, Iterator
_SUPERUSER_ONLY_PREFIXES = (b"COMMENT ON EXTENSION", b"ALTER DEFAULT PRIVILEGES")
_EMPTY_PRECLEAN_SQL = Path(__file__).parent / "empty_preclean.sql"
def filter_superuser_only_lines(lines: Iterable[bytes]) -> Iterator[bytes]:
"""Drop superuser-only statements an app-level psql replay cannot run.
Args:
lines: dump lines including their trailing newlines.
Yields:
Every line except top-level statements starting with a superuser-only
prefix. Lines inside COPY ... FROM stdin data blocks are passed
through untouched: a data row may legally start with the same bytes,
and dropping it would silently corrupt the restored table.
"""
in_copy = False
for line in lines:
if in_copy:
yield line
if line.rstrip(b"\r\n") == b"\\.":
in_copy = False
continue
if line.startswith(b"COPY ") and line.rstrip(b"\r\n").endswith(b"FROM stdin;"):
in_copy = True
yield line
continue
if line.startswith(_SUPERUSER_ONLY_PREFIXES):
continue
yield line
def restore_postgres_sql(
*,
container: str,
db_name: str,
user: str,
password: str,
sql_path: str,
empty: bool,
check_version: bool = True,
) -> None:
if not Path(sql_path).is_file():
raise FileNotFoundError(sql_path)
if check_version:
guard(
sql_path=sql_path,
engine="postgres",
container=container,
user=user,
password=password,
)
docker_env = {"PGPASSWORD": password}
if empty:
with _EMPTY_PRECLEAN_SQL.open(encoding="utf-8") as preclean:
drop_sql = preclean.read()
docker_exec(
container,
["psql", "-v", "ON_ERROR_STOP=1", "-U", user, "-d", db_name],
stdin=drop_sql.encode(),
docker_env=docker_env,
)
# Filter into a spooled temp file instead of building the whole dump in
# memory: production dumps reach many GB and the previous read/splitlines/
# join needed roughly three times the dump size in RSS.
with Path(sql_path).open("rb") as src, tempfile.TemporaryFile() as filtered:
for line in filter_superuser_only_lines(src):
filtered.write(line)
filtered.seek(0)
docker_exec(
container,
[
"psql",
"--single-transaction",
"-v",
"ON_ERROR_STOP=1",
"-U",
user,
"-d",
db_name,
],
stdin=filtered,
docker_env=docker_env,
)
print(f"PostgreSQL restore complete for db '{db_name}'.")