added subcommand to clean deleted relations for issue # 2444

nominatim/clicmd/admin.py

@@ -41,6 +41,8 @@ class AdminFuncs:
                           help='Print performance analysis of the indexing process')
         objs.add_argument('--collect-os-info', action="store_true",
                           help="Generate a report about the host system information")
+        objs.add_argument('--clean-deleted', action='store_true',
+                          help='Clean up deleted relations')
         group = parser.add_argument_group('Arguments for cache warming')
         group.add_argument('--search-only', action='store_const', dest='target',
                            const='search',
@@ -54,8 +56,13 @@ class AdminFuncs:
                             help='Analyse indexing of the given OSM object')
         mgroup.add_argument('--place-id', type=int,
                             help='Analyse indexing of the given Nominatim object')
+        group = parser.add_argument_group('Arguments for cleaning deleted')
+        group.add_argument('--age', type=str,
+                           help='Delete relations older than the given PostgreSQL time interval')
+
 
     def run(self, args: NominatimArgs) -> int:
+        # pylint: disable=too-many-return-statements
         if args.warm:
             return self._warm(args)
 
@@ -81,6 +88,12 @@ class AdminFuncs:
             collect_os_info.report_system_information(args.config)
             return 0
 
+        if args.clean_deleted:
+            LOG.warning('Cleaning up deleted relations')
+            from ..tools import admin
+            admin.clean_deleted_relations(args.config, age=args.age)
+            return 0
+
         return 1
 
 

nominatim/clicmd/args.py

@@ -72,10 +72,12 @@ class NominatimArgs:
     check_database: bool
     migrate: bool
     collect_os_info: bool
+    clean_deleted: bool
     analyse_indexing: bool
     target: Optional[str]
     osm_id: Optional[str]
     place_id: Optional[int]
+    age: str
 
     # Arguments to 'import'
     osm_file: List[str]

nominatim/tools/admin.py

@@ -11,6 +11,7 @@ from typing import Optional, Tuple, Any, cast
 import logging
 
 from psycopg2.extras import Json, register_hstore
+from psycopg2 import DataError
 
 from nominatim.config import Configuration
 from nominatim.db.connection import connect, Cursor
@@ -87,3 +88,23 @@ def analyse_indexing(config: Configuration, osm_id: Optional[str] = None,
 
         for msg in conn.notices:
             print(msg)
+
+
+def clean_deleted_relations(config: Configuration, age: Optional[str] = None) -> None:
+    """ Clean deleted relations older than a given age
+    """
+    if not age:
+        LOG.fatal('No age given to delete relations')
+        raise UsageError('Age parameter not found')
+    with connect(config.get_libpq_dsn()) as conn:
+        with conn.cursor() as cur:
+            try:
+                cur.execute("""SELECT place_force_delete(p.place_id)
+                            FROM import_polygon_delete d, placex p
+                            WHERE p.osm_type = d.osm_type AND p.osm_id = d.osm_id
+                            AND age(p.indexed_date) > %s::interval""",
+                            (age, ))
+            except DataError as exc:
+                raise UsageError('Invalid PostgreSQL time interval format') from exc
+        conn.commit()
+