Release version 3.1.2

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

.claude/.gitignore

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

.claude/settings.json

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

.gitignore

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

CHANGELOG.md

@@ -1,5 +1,47 @@
 # 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
+  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 \
-		test-e2e test test-unit test-integration
+.PHONY: install build clean \
+		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 .
 
-# ------------------------------------------------------------
-# Run E2E tests inside the container (Docker socket required)
-# ------------------------------------------------------------
-# E2E via isolated Docker-in-Docker (DinD)
-# - depends on local image build
-# - starts a DinD daemon container on a dedicated network
-# - loads the freshly built image into DinD
-# - runs the unittest suite inside a container that talks to DinD via DOCKER_HOST
-test-e2e: clean build
-	@bash scripts/test-e2e.sh
+# clean + build run once and in order, then the three suites run concurrently
+# via -j3; the *-run targets carry no clean/build prereq so the sub-make cannot
+# race a second clean against build.
+test:
+	@$(MAKE) clean
+	@$(MAKE) build
+	@$(MAKE) -j3 test-unit-run test-integration-run test-e2e-run
 
-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 = "3.1.2"
 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

@@ -53,12 +53,16 @@ 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;
-BEGIN
-  FOR r IN (
-    SELECT c.relname AS name,
+SELECT format('DROP %s IF EXISTS public.%s CASCADE', obj.type, obj.name)
+  FROM (
+    SELECT format('%I', c.relname) AS name,
            CASE c.relkind
              WHEN 'v' THEN 'VIEW'
              WHEN 'm' THEN 'MATERIALIZED VIEW'
@@ -69,18 +73,20 @@ BEGIN
      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
@@ -89,14 +95,28 @@ BEGIN
                   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
-  ) LOOP
-    EXECUTE format('DROP %s IF EXISTS public.%I CASCADE', r.type, r.name);
-  END LOOP;
-END $$;
+    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)
+  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 +1,186 @@
+# 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.
+# 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);"
+    "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 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;"
+)
+
+
+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",
+        )
+
+    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()

tests/unit/restore/test_postgres_empty_drop.py

@@ -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()