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>

src/baudolo/restore/db/postgres.py

@@ -99,6 +99,16 @@ SELECT format('DROP %s IF EXISTS public.%s CASCADE', obj.type, obj.name)
       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)

tests/e2e/test_e2e_postgres_empty_drop_hard.py

@@ -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()

tests/unit/restore/test_postgres_empty_drop.py

@@ -1,57 +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.%s CASCADE", sql)
-
-    def test_functions_drop_with_identity_signature(self) -> None:
-        """Overloaded functions share a proname; a signature-less DROP aborts
-        with "function name is not unique", so the function branch must emit
-        name(identity args) while every other branch stays %I-quoted."""
-        sql = self._drop_sql()
-        self.assertIn("pg_get_function_identity_arguments(p.oid)", sql)
-        self.assertIn("format('%I(%s)', p.proname", sql)
-        for branch in (
-            "format('%I', c.relname)",
-            "format('%I', t.typname)",
-            "format('%I', col.collname)",
-        ):
-            self.assertIn(branch, sql)
-
-
-if __name__ == "__main__":
-    unittest.main()