Kevin Veen-BirkenbachandClaude Opus 5
bb647c66ec
A restore with --empty destroys before it replays: the pre-clean drops the schema in one session and the dump goes in the next, with no rollback across the two. A dump the engine cannot parse therefore does not fail harmlessly, it leaves an emptied database behind. The version each side is on decides that up front, so the refusal lands before the first session opens. Both engines state their origin in the dump's own header and spell it differently. Postgres names the source server; MariaDB opens with mariadb-dump's own version and names the server further down, so matching the first number would read the tool on one engine and the server on the other. A pg_dumpall stream carries no version line of its own at all - the first belongs to the first database's embedded pg_dump output, arbitrarily far down - hence the deep scan. Restoring forward across a major version stays allowed; that is the upgrade path. Only backward is refused, with --no-version-check as the way out. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
100 lines
2.9 KiB
Python
100 lines
2.9 KiB
Python
from __future__ import annotations
|
|
|
|
import os
|
|
import tempfile
|
|
from collections.abc import Iterable, Iterator
|
|
|
|
from ..run import docker_exec
|
|
from .version import guard
|
|
|
|
_SUPERUSER_ONLY_PREFIXES = (b"COMMENT ON EXTENSION", b"ALTER DEFAULT PRIVILEGES")
|
|
_EMPTY_PRECLEAN_SQL = os.path.join(os.path.dirname(__file__), "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 os.path.isfile(sql_path):
|
|
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 open(_EMPTY_PRECLEAN_SQL, 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 open(sql_path, "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}'.")
|