mirror of
https://github.com/kevinveenbirkenbach/docker-volume-backup.git
synced 2026-08-20 21:22:54 +00:00
build(lint): gate make test on a clean ruff run
ruff was never wired into this repository: no target, no CI step, no pin. It reported 45 findings across sources and tests, so nothing enforced what the codebase already mostly followed. Adds `make ruff` (check + format --check), `make ruff-fix`, and `make lint` as its alias, and makes `make test` run lint as a fourth parallel spur. The CI workflow calls `make test`, so it is covered there too. The linter is pinned in a `lint` extra: a ruff minor bump changes which rules fire, and with the suite gating on a clean run an unpinned linter would fail it on an unrelated day. The 45 findings are fixed rather than configured away. Three needed a decision instead of the mechanical fix: - The generation timestamp keeps its local wall clock (DTZ005 waived). Generations sort by that name, and UTC would order new ones before the existing ones wherever the offset is positive - "newest generation" is what every restore path selects on. - The per-volume `copy` closure now binds volume_name and vol_dir as default arguments (B023). It only worked because it is called inside the same iteration. - The two CLI top-level handlers keep their blind except (BLE001 waived): turning any failure into exit 1 is what a CLI boundary is for. The two in run.py did not need it and were narrowed to what they actually catch. Also drops the comments that restate the code: the section banners in restore/__main__.py, the filename repeated as line 1 of nine test files, step narration above the statement it narrates, and a block in app.py documenting parameters that had moved to another module. What names a trip-wire stays - the snapshot destination rule, the mysql-binary absence in MariaDB 11 images, the session-scoped FOREIGN_KEY_CHECKS, the spooled temp file for multi-GB dumps, and the negative control that loses its discriminating power if it ever passes. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -1,9 +1,6 @@
|
||||
#!/usr/bin/env python3
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from .app import main
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
|
||||
@@ -30,17 +30,13 @@ def main() -> int:
|
||||
args = parse_args()
|
||||
|
||||
machine_id = get_machine_id()
|
||||
backup_time = datetime.now().strftime("%Y%m%d%H%M%S")
|
||||
# Local wall clock on purpose: generations sort by this name, and UTC would
|
||||
# order new ones before the existing ones wherever the offset is positive.
|
||||
backup_time = datetime.now().strftime("%Y%m%d%H%M%S") # noqa: DTZ005
|
||||
|
||||
versions_dir = os.path.join(args.backups_dir, machine_id, args.repo_name)
|
||||
version_dir = create_version_directory(versions_dir, backup_time)
|
||||
|
||||
# IMPORTANT:
|
||||
# - keep_default_na=False prevents empty fields from turning into NaN
|
||||
# - dtype=str keeps all columns stable for comparisons/validation
|
||||
#
|
||||
# Robust behavior:
|
||||
# - if the file is missing or empty, we continue without DB dumps.
|
||||
databases_df = load_databases_df(args.databases_csv)
|
||||
|
||||
print("💾 Start volume backups...", flush=True)
|
||||
@@ -80,24 +76,29 @@ def main() -> int:
|
||||
database_containers=args.database_containers,
|
||||
)
|
||||
|
||||
if args.dump_only_sql:
|
||||
if found_db:
|
||||
if not dumped_any:
|
||||
print(
|
||||
f"WARNING: dump-only-sql requested but no DB dump was produced for DB volume '{volume_name}'. "
|
||||
"Falling back to file backup.",
|
||||
flush=True,
|
||||
)
|
||||
else:
|
||||
continue
|
||||
if args.dump_only_sql and found_db:
|
||||
if not dumped_any:
|
||||
print(
|
||||
f"WARNING: dump-only-sql requested but no DB dump was produced for DB volume '{volume_name}'. "
|
||||
"Falling back to file backup.",
|
||||
flush=True,
|
||||
)
|
||||
else:
|
||||
continue
|
||||
|
||||
live_source = get_storage_path(volume_name)
|
||||
|
||||
def copy(*, authoritative: bool, source: str = live_source) -> None:
|
||||
def copy(
|
||||
*,
|
||||
authoritative: bool,
|
||||
source: str = live_source,
|
||||
volume: str = volume_name,
|
||||
target: str = vol_dir,
|
||||
) -> None:
|
||||
backup_volume(
|
||||
versions_dir,
|
||||
volume_name,
|
||||
vol_dir,
|
||||
volume,
|
||||
target,
|
||||
authoritative=authoritative,
|
||||
source=source,
|
||||
)
|
||||
|
||||
@@ -4,10 +4,9 @@ import os
|
||||
import shutil
|
||||
import subprocess
|
||||
from pathlib import Path
|
||||
from typing import List, Optional
|
||||
|
||||
|
||||
def _build_compose_cmd(project_dir: str, passthrough: List[str]) -> List[str]:
|
||||
def _build_compose_cmd(project_dir: str, passthrough: list[str]) -> list[str]:
|
||||
"""
|
||||
Build the compose command for this project directory.
|
||||
|
||||
@@ -30,7 +29,7 @@ def _build_compose_cmd(project_dir: str, passthrough: List[str]) -> List[str]:
|
||||
raise RuntimeError("Neither 'compose' nor 'docker' found in PATH")
|
||||
|
||||
|
||||
def _find_compose_file(project_dir: str) -> Optional[Path]:
|
||||
def _find_compose_file(project_dir: str) -> Path | None:
|
||||
"""
|
||||
Detect a compose file in `project_dir` (case-insensitive).
|
||||
|
||||
|
||||
@@ -1,10 +1,9 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import os
|
||||
import pathlib
|
||||
import re
|
||||
import logging
|
||||
from typing import Optional
|
||||
|
||||
import pandas
|
||||
|
||||
@@ -22,7 +21,7 @@ def get_instance(container: str, database_containers: list[str]) -> str:
|
||||
return re.split(r"(_|-)(database|db|postgres)", container)[0]
|
||||
|
||||
|
||||
def _validate_database_value(value: Optional[str], *, instance: str) -> str:
|
||||
def _validate_database_value(value: str | None, *, instance: str) -> str:
|
||||
"""
|
||||
Enforce explicit database semantics:
|
||||
|
||||
@@ -70,7 +69,7 @@ def backup_database(
|
||||
container: str,
|
||||
volume_dir: str,
|
||||
db_type: str,
|
||||
databases_df: "pandas.DataFrame",
|
||||
databases_df: pandas.DataFrame,
|
||||
database_containers: list[str],
|
||||
) -> bool:
|
||||
"""
|
||||
@@ -97,7 +96,6 @@ def backup_database(
|
||||
|
||||
db_value = _validate_database_value(raw_db, instance=instance_name)
|
||||
|
||||
# Explicit: dump ALL databases
|
||||
if db_value == "*":
|
||||
if db_type != "postgres":
|
||||
raise ValueError(
|
||||
@@ -110,7 +108,6 @@ def backup_database(
|
||||
produced = True
|
||||
continue
|
||||
|
||||
# Concrete database dump
|
||||
db_name = db_value
|
||||
dump_file = os.path.join(out_dir, f"{db_name}.backup.sql")
|
||||
|
||||
@@ -135,7 +132,6 @@ def backup_database(
|
||||
_atomic_write_cmd(cmd, dump_file)
|
||||
produced = True
|
||||
except BackupException as e:
|
||||
# Explicit DB dump failed -> hard error
|
||||
raise BackupException(
|
||||
f"Postgres dump failed for instance '{instance_name}', "
|
||||
f"database '{db_name}'. This database was explicitly configured "
|
||||
|
||||
@@ -98,5 +98,5 @@ def docker_volume_exists(volume: str) -> bool:
|
||||
f"docker volume inspect {volume} >/dev/null 2>&1 && echo OK"
|
||||
)
|
||||
return True
|
||||
except Exception:
|
||||
except BackupException:
|
||||
return False
|
||||
|
||||
@@ -15,7 +15,7 @@ def backup_mariadb_or_postgres(
|
||||
*,
|
||||
container: str,
|
||||
volume_dir: str,
|
||||
databases_df: "pandas.DataFrame",
|
||||
databases_df: pandas.DataFrame,
|
||||
database_containers: list[str],
|
||||
) -> tuple[bool, bool]:
|
||||
"""
|
||||
@@ -34,7 +34,7 @@ def backup_mariadb_or_postgres(
|
||||
return False, False
|
||||
|
||||
|
||||
def _empty_databases_df() -> "pandas.DataFrame":
|
||||
def _empty_databases_df() -> pandas.DataFrame:
|
||||
"""
|
||||
Create an empty DataFrame with the expected schema for databases.csv.
|
||||
|
||||
@@ -44,7 +44,7 @@ def _empty_databases_df() -> "pandas.DataFrame":
|
||||
return pandas.DataFrame(columns=["instance", "database", "username", "password"])
|
||||
|
||||
|
||||
def load_databases_df(csv_path: str) -> "pandas.DataFrame":
|
||||
def load_databases_df(csv_path: str) -> pandas.DataFrame:
|
||||
"""
|
||||
Load databases.csv robustly.
|
||||
|
||||
@@ -74,7 +74,7 @@ def backup_dumps_for_volume(
|
||||
*,
|
||||
containers: list[str],
|
||||
vol_dir: str,
|
||||
databases_df: "pandas.DataFrame",
|
||||
databases_df: pandas.DataFrame,
|
||||
database_containers: list[str],
|
||||
) -> tuple[bool, bool]:
|
||||
"""
|
||||
|
||||
Reference in New Issue
Block a user