6 Commits

Author SHA1 Message Date
d2ba2eb5ae Release version 3.1.2 2026-07-18 00:39:10 +02:00
6a016d7a58 chore(claude): ignore local runtime state under .claude, keep settings.json
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-18 00:38:38 +02:00
d1d5445b1d chore(claude): pause for confirmation before CHANGELOG or pyproject edits
Release metadata (version bump and changelog entry) stays a manual step; agent edits to CHANGELOG.md and pyproject.toml now require explicit operator approval. The local .mcp.json is ignored.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-18 00:37:28 +02:00
bd267cc280 fix(restore): drop text search objects in the postgres --empty pre-clean
A schema shipping a custom text search dictionary (taiga's english_stem_nostop) survived the pre-clean and aborted the dump replay with a duplicate pg_ts_dict_dictname_index violation under ON_ERROR_STOP. The discovery SELECT now also enumerates user-owned pg_ts_config and pg_ts_dict entries. The string-assertion unit test is replaced by real scenario data in the e2e: the seeded schema now contains an overloaded f()/f(int) pair and the nostop dictionary plus configuration, and the restored database is queried to prove each survives the backup, pre-clean and replay cycle exactly once.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-18 00:34:53 +02:00
53460242d8 Release version 3.1.1 2026-07-17 17:28:54 +02:00
01a00dd791 fix(restore): drop overloaded functions by identity signature in the --empty pre-clean
A signature-less DROP FUNCTION aborts with 'function name is not unique' as soon as a schema overloads a name, killing the whole --empty replay under ON_ERROR_STOP. The function branch now emits name(identity args) via pg_get_function_identity_arguments; because that compound must not be identifier-quoted as a whole, quoting moves from the outer format into each branch, guarded by a unit test that pins the per-branch %I quoting.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-17 17:27:55 +02:00
8 changed files with 88 additions and 51 deletions

3
.claude/.gitignore vendored Normal file
View File

@@ -0,0 +1,3 @@
*
!.gitignore
!settings.json

10
.claude/settings.json Normal file
View File

@@ -0,0 +1,10 @@
{
"permissions": {
"ask": [
"Edit(CHANGELOG.md)",
"Write(CHANGELOG.md)",
"Edit(pyproject.toml)",
"Write(pyproject.toml)"
]
}
}

3
.gitignore vendored
View File

@@ -2,4 +2,5 @@ __pycache__
artifacts/
*.egg-info
dist/
build/
build/
.mcp.json

View File

@@ -1,5 +1,30 @@
# Changelog
## [3.1.2] - 2026-07-18
- Restore: the postgres *--empty* pre-clean also drops user-owned text
search configurations and dictionaries (*pg_ts_config*, *pg_ts_dict*),
so a schema shipping a custom dictionary (e.g. taiga's
*english_stem_nostop*) no longer aborts the replay with "duplicate key
value violates unique constraint pg_ts_dict_dictname_index" under
ON_ERROR_STOP.
- Tests: the string-assertion unit test for the pre-clean SQL is replaced
by real scenario data in the e2e: the seeded schema contains an
overloaded *f()/f(int)* pair and the nostop dictionary plus
configuration, and the restored database is queried to prove each
survives the backup, pre-clean and replay cycle exactly once.
## [3.1.1] - 2026-07-17
- Restore: the postgres *--empty* pre-clean drops functions and procedures
by their identity signature (*pg_get_function_identity_arguments*), so a
schema that overloads a function name (e.g. discourse) no longer aborts
the replay with "function name is not unique" under ON_ERROR_STOP.
Identifier quoting moves from the outer DROP format into each object
branch, since the *name(args)* compound must not be quoted as a whole; a
unit test pins the per-branch *%I* quoting so future branches cannot
regress unquoted.
## [3.1.0] - 2026-07-15
- Restore: the postgres *--empty* pre-clean emits one DROP per object and

View File

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
[project]
name = "backup-docker-to-local"
version = "3.1.0"
version = "3.1.2"
description = "Backup Docker volumes to local with rsync and optional DB dumps."
readme = "README.md"
requires-python = ">=3.9"

View File

@@ -60,9 +60,9 @@ def restore_postgres_sql(
# discourse's discourse_functions) does not fail on an already-existing schema.
# Extension members (pg_trgm's set_limit) are superuser-owned; IF EXISTS absorbs CASCADE fallout.
drop_sql = r"""
SELECT format('DROP %s IF EXISTS public.%I CASCADE', obj.type, obj.name)
SELECT format('DROP %s IF EXISTS public.%s CASCADE', obj.type, obj.name)
FROM (
SELECT c.relname AS name,
SELECT format('%I', c.relname) AS name,
CASE c.relkind
WHEN 'v' THEN 'VIEW'
WHEN 'm' THEN 'MATERIALIZED VIEW'
@@ -73,18 +73,20 @@ SELECT format('DROP %s IF EXISTS public.%I CASCADE', obj.type, obj.name)
WHERE n.nspname = 'public' AND c.relkind IN ('r', 'p', 'v', 'm', 'f')
AND pg_get_userbyid(c.relowner) = current_user
UNION ALL
SELECT p.proname AS name,
-- Overloaded functions share a proname; DROP needs the identity
-- signature or psql aborts with "function name is not unique".
SELECT format('%I(%s)', p.proname, pg_get_function_identity_arguments(p.oid)) AS name,
CASE p.prokind WHEN 'p' THEN 'PROCEDURE' ELSE 'FUNCTION' END AS type
FROM pg_proc p JOIN pg_namespace n ON n.oid = p.pronamespace
WHERE n.nspname = 'public' AND p.prokind IN ('f', 'p', 'w')
AND pg_get_userbyid(p.proowner) = current_user
UNION ALL
SELECT c.relname AS name, 'SEQUENCE' AS type
SELECT format('%I', c.relname) AS name, 'SEQUENCE' AS type
FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace
WHERE n.nspname = 'public' AND c.relkind = 'S'
AND pg_get_userbyid(c.relowner) = current_user
UNION ALL
SELECT t.typname AS name, 'TYPE' AS type
SELECT format('%I', t.typname) AS name, 'TYPE' AS type
FROM pg_type t JOIN pg_namespace n ON n.oid = t.typnamespace
WHERE n.nspname = 'public'
AND pg_get_userbyid(t.typowner) = current_user
@@ -93,10 +95,20 @@ SELECT format('DROP %s IF EXISTS public.%I CASCADE', obj.type, obj.name)
SELECT 1 FROM pg_class c2
WHERE c2.oid = t.typrelid AND c2.relkind = 'c')))
UNION ALL
SELECT col.collname AS name, 'COLLATION' AS type
SELECT format('%I', col.collname) AS name, 'COLLATION' AS type
FROM pg_collation col JOIN pg_namespace n ON n.oid = col.collnamespace
WHERE n.nspname = 'public'
AND pg_get_userbyid(col.collowner) = current_user
UNION ALL
SELECT format('%I', ts.cfgname) AS name, 'TEXT SEARCH CONFIGURATION' AS type
FROM pg_ts_config ts JOIN pg_namespace n ON n.oid = ts.cfgnamespace
WHERE n.nspname = 'public'
AND pg_get_userbyid(ts.cfgowner) = current_user
UNION ALL
SELECT format('%I', d.dictname) AS name, 'TEXT SEARCH DICTIONARY' AS type
FROM pg_ts_dict d JOIN pg_namespace n ON n.oid = d.dictnamespace
WHERE n.nspname = 'public'
AND pg_get_userbyid(d.dictowner) = current_user
) obj
UNION ALL
SELECT format('DROP SCHEMA IF EXISTS %I CASCADE', n.nspname)

View File

@@ -21,6 +21,9 @@ from .helpers import (
# --empty runs against the still-populated DB (no wipe), so the pre-clean must
# drop discourse_functions too or the dump's CREATE SCHEMA aborts the replay
# under ON_ERROR_STOP; the old public-only DROP left it and broke discourse.
# The f()/f(int) pair reproduces discourse's overload abort ("function name
# is not unique") and english_stem_nostop reproduces taiga's text search
# dictionary abort (duplicate pg_ts_dict_dictname_index).
SCENARIO_SQL = (
"CREATE SCHEMA discourse_functions;"
"CREATE TABLE discourse_functions.helper (id int);"
@@ -31,7 +34,13 @@ SCENARIO_SQL = (
"CREATE SEQUENCE public.s;"
"CREATE TYPE public.mood AS ENUM ('ok', 'bad');"
"CREATE FUNCTION public.f() RETURNS int LANGUAGE sql AS 'SELECT 1';"
"CREATE FUNCTION public.f(i int) RETURNS int LANGUAGE sql AS 'SELECT i';"
"CREATE COLLATION public.c (locale = 'C');"
"CREATE TEXT SEARCH DICTIONARY public.english_stem_nostop"
" (Template = snowball, Language = english);"
"CREATE TEXT SEARCH CONFIGURATION public.english_nostop (COPY = english);"
"ALTER TEXT SEARCH CONFIGURATION public.english_nostop"
" ALTER MAPPING FOR asciiword WITH public.english_stem_nostop;"
)
@@ -152,6 +161,26 @@ class TestE2EPostgresEmptyDropHard(unittest.TestCase):
"1",
)
def test_overloaded_functions_restored_once_each(self) -> None:
self.assertEqual(
self._scalar("SELECT count(*) FROM pg_proc WHERE proname='f';"), "2"
)
self.assertEqual(self._scalar("SELECT public.f(41) + public.f();"), "42")
def test_text_search_dictionary_restored_once(self) -> None:
self.assertEqual(
self._scalar(
"SELECT count(*) FROM pg_ts_dict WHERE dictname='english_stem_nostop';"
),
"1",
)
self.assertEqual(
self._scalar(
"SELECT count(*) FROM pg_ts_config WHERE cfgname='english_nostop';"
),
"1",
)
if __name__ == "__main__":
unittest.main()

View File

@@ -1,43 +0,0 @@
"""The --empty pre-clean drop must cover every object class a dump can
re-CREATE ahead of tables; a missed class aborts the replay under
ON_ERROR_STOP (OpenProject's ICU collation public.versions_name did)."""
import tempfile
import unittest
from pathlib import Path
from unittest import mock
from baudolo.restore.db import postgres
class TestPostgresEmptyDrop(unittest.TestCase):
def _drop_sql(self) -> str:
with tempfile.NamedTemporaryFile(suffix=".sql") as fh:
Path(fh.name).write_bytes(b"SELECT 1;\n")
with mock.patch.object(postgres, "docker_exec") as run:
postgres.restore_postgres_sql(
container="c",
db_name="db",
user="u",
password="p",
sql_path=fh.name,
empty=True,
)
first_call = run.call_args_list[0]
return first_call.kwargs["stdin"].decode()
def test_drop_covers_collations(self) -> None:
sql = self._drop_sql()
self.assertIn("pg_collation", sql)
self.assertIn("'COLLATION' AS type", sql)
self.assertIn("pg_get_userbyid(col.collowner) = current_user", sql)
def test_drop_still_covers_the_other_classes(self) -> None:
sql = self._drop_sql()
for marker in ("pg_class", "pg_proc", "'SEQUENCE' AS type", "'TYPE' AS type"):
self.assertIn(marker, sql)
self.assertIn("DROP %s IF EXISTS public.%I CASCADE", sql)
if __name__ == "__main__":
unittest.main()