Files
docker-volume-backup/tests/unit/backup/test_db_mariadb_dump.py
Kevin Veen-Birkenbach f791046c02 fix(backup): detect the engine by its dump tool, not by the image name
36b2336 matched postgres and mariadb against the image's repository path. That name is not a property of the software: a dedicated Postgres inside an app's own stack is tagged <app>-database or postgis/postgis and carries no engine token at all, so it was never recognised, never dumped, and its data directory was copied as files without a single warning - the fallback notice hangs on found_db, which stayed false.

The container is now asked what it can run. pg_dumpall, mariadb-dump and mysqldump are probed by executing them, not by asking a shell for them, because a distroless image has no shell and would deny every tool it ships. The verdict is cached per image ID rather than per container, so replicas of one image cost a single probe.

Because the probe names the tool it found, the dump uses it instead of the hardcoded /usr/bin/mariadb-dump, which makes an image that ships only mysqldump dumpable rather than silently file-copied.

image_name and has_image are gone with their registry-host and tag stripping; the trap they worked around cannot occur when nothing reads the name. get_image_info stays, since the --images-* lists match exact references.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-17 13:51:26 +02:00

87 lines
2.6 KiB
Python

import tempfile
import unittest
from unittest.mock import patch
import pandas
from baudolo.backup import db as db_mod
def _df(rows):
return pandas.DataFrame(
rows, columns=["instance", "database", "username", "password"]
)
def _capture_commands(*, db_type, rows, container, dump_tool="mariadb-dump"):
captured = []
def _capture(cmd):
captured.append(cmd)
return []
with (
tempfile.TemporaryDirectory() as td,
patch.object(db_mod, "execute_shell_command", side_effect=_capture),
):
db_mod.backup_database(
container=container,
volume_dir=td,
db_type=db_type,
dump_tool=dump_tool,
databases_df=_df(rows),
database_containers=[container],
)
return captured
class TestMariaDBDumpUsesTCP(unittest.TestCase):
# Regression guard for 'Access denied for user <user>@localhost' when only
# '<user>'@'%' is granted: the in-container mariadb-dump MUST force TCP so
# the connection is auth-matched against '%' instead of socket->localhost.
def test_mariadb_dump_forces_tcp_loopback(self):
captured = _capture_commands(
db_type="mariadb",
rows=[("mariadb", "appdb", "appuser", "s3cret")],
container="mariadb",
)
dump_cmds = [c for c in captured if "mariadb-dump" in c]
self.assertEqual(
len(dump_cmds), 1, f"expected one dump command, got: {captured}"
)
cmd = dump_cmds[0]
self.assertIn("-h 127.0.0.1", cmd)
self.assertIn("--protocol=tcp", cmd)
self.assertIn("-u appuser", cmd)
self.assertIn("-ps3cret", cmd)
self.assertIn(" appdb", cmd)
def test_the_probed_client_is_the_one_invoked(self):
captured = _capture_commands(
db_type="mariadb",
rows=[("mariadb", "appdb", "appuser", "s3cret")],
container="mariadb",
dump_tool="mysqldump",
)
dump_cmds = [c for c in captured if "mysqldump" in c]
self.assertEqual(
len(dump_cmds), 1, f"expected one dump command, got: {captured}"
)
self.assertNotIn("mariadb-dump", dump_cmds[0])
def test_postgres_dump_unaffected(self):
captured = _capture_commands(
db_type="postgres",
rows=[("pg", "appdb", "appuser", "s3cret")],
container="pg",
)
dump_cmds = [c for c in captured if "pg_dump" in c and "pg_dumpall" not in c]
self.assertEqual(len(dump_cmds), 1)
self.assertNotIn("--protocol=tcp", dump_cmds[0])
if __name__ == "__main__":
unittest.main(verbosity=2)