Release version 3.1.0

Both default to an empty list so a pure file backup needs no dummy
arguments; an empty stop whitelist keeps the conservative stop-all
behavior.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

CHANGELOG.md

@@ -1,5 +1,22 @@
 # Changelog
 
+## [3.1.0] - 2026-07-15
+
+- Restore: the postgres *--empty* pre-clean emits one DROP per object and
+  runs them via *\gexec* instead of a single DO-block, so large schemas
+  (e.g. gitlab) no longer exhaust *max_locks_per_transaction* in one
+  transaction. It also drops user-owned non-public schemas, so dumps that
+  CREATE SCHEMA (e.g. discourse's *discourse_functions*) no longer abort
+  on the already-existing schema under ON_ERROR_STOP.
+- Backup: *--database-containers* and *--images-no-stop-required* are now
+  optional and default to an empty list, so a pure file backup needs no
+  dummy arguments; an empty stop whitelist keeps the conservative
+  stop-all behavior.
+- Tests: new e2e test restores *--empty* against a fully populated
+  database containing a non-public schema and every dropped object class.
+  *make test* runs the three suites concurrently after a single
+  clean+build; *E2E_TEST_PATTERN* runs an e2e subset.
+
 ## [3.0.0] - 2026-07-12
 
 - Backup: *--images-no-stop-required* and *--images-no-backup-required* now

Makefile

@@ -1,5 +1,6 @@
-.PHONY: install build \
+.PHONY: install build clean \
-		test-e2e test test-unit test-integration
+		test test-unit test-integration test-e2e \
+		test-unit-run test-integration-run test-e2e-run
 
 # Default python if no venv is active
 PY_DEFAULT ?= python3
@@ -33,25 +34,32 @@ build:
 clean:
 	git clean -fdX .
 
-# ------------------------------------------------------------
+# clean + build run once and in order, then the three suites run concurrently
-# Run E2E tests inside the container (Docker socket required)
+# via -j3; the *-run targets carry no clean/build prereq so the sub-make cannot
-# ------------------------------------------------------------
+# race a second clean against build.
-# E2E via isolated Docker-in-Docker (DinD)
+test:
-# - depends on local image build
+	@$(MAKE) clean
-# - starts a DinD daemon container on a dedicated network
+	@$(MAKE) build
-# - loads the freshly built image into DinD
+	@$(MAKE) -j3 test-unit-run test-integration-run test-e2e-run
-# - runs the unittest suite inside a container that talks to DinD via DOCKER_HOST
-test-e2e: clean build
-	@bash scripts/test-e2e.sh
 
-test: test-unit test-integration test-e2e
+test-unit: clean build test-unit-run
 
-test-unit: clean build
+test-integration: clean build test-integration-run
+
+test-e2e: clean build test-e2e-run
+
+test-unit-run:
 	@echo ">> Running unit tests"
 	@docker run --rm -t $(IMAGE) \
 	  bash -lc 'python -m unittest discover -t . -s tests/unit -p "test_*.py" -v'
 
-test-integration: clean build
+test-integration-run:
 	@echo ">> Running integration tests"
 	@docker run --rm -t $(IMAGE) \
-	  bash -lc 'python -m unittest discover -t . -s tests/integration -p "test_*.py" -v'
+	  bash -lc 'python -m unittest discover -t . -s tests/integration -p "test_*.py" -v'
+
+# E2E via isolated Docker-in-Docker (DinD): starts a DinD daemon on a dedicated
+# network, loads the freshly built image into it, and runs tests/e2e inside a
+# container that talks to DinD via DOCKER_HOST.
+test-e2e-run:
+	@bash scripts/test-e2e.sh

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "backup-docker-to-local"
-version = "3.0.0"
+version = "3.1.0"
 description = "Backup Docker volumes to local with rsync and optional DB dumps."
 readme = "README.md"
 requires-python = ">=3.9"

scripts/test-e2e.sh

@@ -37,6 +37,9 @@ KEEP_ON_FAIL="${E2E_KEEP_ON_FAIL:-0}"
 KEEP_VOLUMES="${E2E_KEEP_VOLUMES:-0}"
 DEBUG_SHELL="${E2E_DEBUG_SHELL:-0}"
 
+# Override to run a subset, e.g. E2E_TEST_PATTERN=test_e2e_postgres_empty_drop_hard.py
+TEST_PATTERN="${E2E_TEST_PATTERN:-test_*.py}"
+
 FAILED=0
 TS="$(date +%Y%m%d%H%M%S)"
 
@@ -194,6 +197,7 @@ else
   docker run --rm \
     --network "${NET}" \
     -e DOCKER_HOST="${DIND_HOST_IN_NET}" \
+    -e E2E_TEST_PATTERN="${TEST_PATTERN}" \
     -v "${DIND_VOL}:/var/lib/docker" \
     -v "${E2E_TMP_VOL}:/tmp" \
     "${IMG}" \
@@ -209,7 +213,7 @@ else
         cat /proc/sys/kernel/random/uuid > /etc/machine-id
     fi
 
-    python -m unittest discover -t . -s tests/e2e -p "test_*.py" -v -f
+    python -m unittest discover -t . -s tests/e2e -p "${E2E_TEST_PATTERN}" -v -f
     '
   rc=$?
 fi

src/baudolo/backup/cli.py

@@ -42,13 +42,13 @@ def parse_args() -> argparse.Namespace:
     p.add_argument(
         "--database-containers",
         nargs="+",
-        required=True,
+        default=[],
         help="Container names treated as special instances for database backups",
     )
     p.add_argument(
         "--images-no-stop-required",
         nargs="+",
-        required=True,
+        default=[],
         help="Exact image references (repo:tag, incl. any registry prefix) whose containers must not be stopped during file backup",
     )
     p.add_argument(

src/baudolo/restore/db/postgres.py

@@ -53,11 +53,15 @@ def restore_postgres_sql(
     docker_env = {"PGPASSWORD": password}
 
     if empty:
-        # Owner-filtered: extension members (pg_trgm's set_limit) are superuser-owned; IF EXISTS absorbs CASCADE fallout.
+        # Owner-filtered pre-clean emitted as one DROP per row and run via \gexec so each
+        # executes as its own top-level statement: a single DO-block runs every DROP in one
+        # transaction and exhausts max_locks_per_transaction on large schemas (e.g. gitlab).
+        # Also drop user-owned non-public schemas so a dump that CREATE SCHEMAs (e.g.
+        # 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"""
-DO $$ DECLARE r RECORD;
+SELECT format('DROP %s IF EXISTS public.%I CASCADE', obj.type, obj.name)
-BEGIN
+  FROM (
-  FOR r IN (
     SELECT c.relname AS name,
            CASE c.relkind
              WHEN 'v' THEN 'VIEW'
@@ -93,10 +97,14 @@ BEGIN
       FROM pg_collation col JOIN pg_namespace n ON n.oid = col.collnamespace
      WHERE n.nspname = 'public'
        AND pg_get_userbyid(col.collowner) = current_user
-  ) LOOP
+  ) obj
-    EXECUTE format('DROP %s IF EXISTS public.%I CASCADE', r.type, r.name);
+UNION ALL
-  END LOOP;
+SELECT format('DROP SCHEMA IF EXISTS %I CASCADE', n.nspname)
-END $$;
+  FROM pg_namespace n
+ WHERE NOT starts_with(n.nspname, 'pg_')
+   AND n.nspname NOT IN ('public', 'information_schema')
+   AND pg_get_userbyid(n.nspowner) = current_user
+\gexec
 """
         docker_exec(
             container,

tests/e2e/test_e2e_postgres_empty_drop_hard.py

@@ -0,0 +1,157 @@
+# tests/e2e/test_e2e_postgres_empty_drop_hard.py
+import unittest
+
+from .helpers import (
+    POSTGRES_IMAGE,
+    POSTGRES_DATA_DIR,
+    backup_run,
+    cleanup_docker,
+    create_minimal_compose_dir,
+    ensure_empty_dir,
+    latest_version_dir,
+    require_docker,
+    run,
+    unique,
+    wait_for_postgres,
+    write_databases_csv,
+)
+
+# The scenario the --empty pre-clean must survive: a non-public user schema
+# plus one object of every class the discovery SELECT enumerates. Restore
+# --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.
+SCENARIO_SQL = (
+    "CREATE SCHEMA discourse_functions;"
+    "CREATE TABLE discourse_functions.helper (id int);"
+    "INSERT INTO discourse_functions.helper VALUES (1);"
+    "CREATE TABLE public.t (id int primary key, v text);"
+    "INSERT INTO public.t VALUES (1, 'ok');"
+    "CREATE VIEW public.t_view AS SELECT * FROM public.t;"
+    "CREATE SEQUENCE public.s;"
+    "CREATE TYPE public.mood AS ENUM ('ok', 'bad');"
+    "CREATE FUNCTION public.f() RETURNS int LANGUAGE sql AS 'SELECT 1';"
+    "CREATE COLLATION public.c (locale = 'C');"
+)
+
+
+class TestE2EPostgresEmptyDropHard(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls) -> None:
+        require_docker()
+        cls.prefix = unique("baudolo-e2e-postgres-empty-drop-hard")
+        cls.backups_dir = f"/tmp/{cls.prefix}/Backups"
+        ensure_empty_dir(cls.backups_dir)
+        cls.compose_dir = create_minimal_compose_dir(f"/tmp/{cls.prefix}")
+        cls.repo_name = cls.prefix
+
+        cls.pg_container = f"{cls.prefix}-pg"
+        cls.pg_volume = f"{cls.prefix}-pg-vol"
+        cls.containers = [cls.pg_container]
+        cls.volumes = [cls.pg_volume]
+
+        run(["docker", "volume", "create", cls.pg_volume])
+        run(
+            [
+                "docker",
+                "run",
+                "-d",
+                "--name",
+                cls.pg_container,
+                "-e",
+                "POSTGRES_PASSWORD=pgpw",
+                "-e",
+                "POSTGRES_DB=appdb",
+                "-e",
+                "POSTGRES_USER=postgres",
+                "-v",
+                f"{cls.pg_volume}:{POSTGRES_DATA_DIR}",
+                POSTGRES_IMAGE,
+            ]
+        )
+        wait_for_postgres(cls.pg_container, user="postgres", timeout_s=90)
+
+        run(
+            [
+                "docker",
+                "exec",
+                cls.pg_container,
+                "sh",
+                "-lc",
+                f'psql -U postgres -d appdb -v ON_ERROR_STOP=1 -c "{SCENARIO_SQL}"',
+            ]
+        )
+
+        cls.databases_csv = f"/tmp/{cls.prefix}/databases.csv"
+        write_databases_csv(
+            cls.databases_csv, [(cls.pg_container, "appdb", "postgres", "pgpw")]
+        )
+        backup_run(
+            backups_dir=cls.backups_dir,
+            repo_name=cls.repo_name,
+            compose_dir=cls.compose_dir,
+            databases_csv=cls.databases_csv,
+            database_containers=[cls.pg_container],
+            images_no_stop_required=[POSTGRES_IMAGE],
+        )
+        cls.hash, cls.version = latest_version_dir(cls.backups_dir, cls.repo_name)
+
+        # No wipe: restore --empty must pre-clean the fully-populated DB
+        # (incl. the non-public schema) before replaying the dump.
+        run(
+            [
+                "baudolo-restore",
+                "postgres",
+                cls.pg_volume,
+                cls.hash,
+                cls.version,
+                "--backups-dir",
+                cls.backups_dir,
+                "--repo-name",
+                cls.repo_name,
+                "--container",
+                cls.pg_container,
+                "--db-name",
+                "appdb",
+                "--db-user",
+                "postgres",
+                "--db-password",
+                "pgpw",
+                "--empty",
+            ]
+        )
+
+    @classmethod
+    def tearDownClass(cls) -> None:
+        cleanup_docker(containers=cls.containers, volumes=cls.volumes)
+
+    def _scalar(self, sql: str) -> str:
+        p = run(
+            [
+                "docker",
+                "exec",
+                self.pg_container,
+                "sh",
+                "-lc",
+                f'psql -U postgres -d appdb -t -A -c "{sql}"',
+            ]
+        )
+        return (p.stdout or "").strip()
+
+    def test_public_data_restored(self) -> None:
+        self.assertEqual(self._scalar("SELECT v FROM public.t WHERE id=1;"), "ok")
+
+    def test_view_restored(self) -> None:
+        self.assertEqual(self._scalar("SELECT count(*) FROM public.t_view;"), "1")
+
+    def test_non_public_schema_restored(self) -> None:
+        self.assertEqual(
+            self._scalar(
+                "SELECT count(*) FROM pg_namespace WHERE nspname='discourse_functions';"
+            ),
+            "1",
+        )
+
+
+if __name__ == "__main__":
+    unittest.main()