reintroduce cutoffs when searching for very frequent words

[nominatim.git] / nominatim / clicmd / setup.py

diff --git a/nominatim/clicmd/setup.py b/nominatim/clicmd/setup.py
index ca3bf40ed3116ffe7890518511e449b401f1575e..ccd6bd788ed315a45bc8d2e7b2d872bdb64c8de5 100644 (file)
--- a/nominatim/clicmd/setup.py
+++ b/nominatim/clicmd/setup.py
@@ -39,8 +39,7 @@ class SetupAll:
     """
 
     def add_args(self, parser: argparse.ArgumentParser) -> None:
     """
 
     def add_args(self, parser: argparse.ArgumentParser) -> None:

-        group_name = parser.add_argument_group('Required arguments')
-        group1 = group_name.add_argument_group()
+        group1 = parser.add_argument_group('Required arguments')

         group1.add_argument('--osm-file', metavar='FILE', action='append',
                            help='OSM file to be imported'
                                 ' (repeat for importing multiple files)',
         group1.add_argument('--osm-file', metavar='FILE', action='append',
                            help='OSM file to be imported'
                                 ' (repeat for importing multiple files)',


@@ -101,7 +100,7 @@ class SetupAll:
 
         if args.continue_at in (None, 'import-from-file'):
             files = args.get_osm_file_list()
 
         if args.continue_at in (None, 'import-from-file'):
             files = args.get_osm_file_list()

-            if not files and not args.prepare_database:
+            if not files:

                 raise UsageError("No input files (use --osm-file).")
 
             if args.continue_at in ('import-from-file', None):
                 raise UsageError("No input files (use --osm-file).")
 
             if args.continue_at in ('import-from-file', None):


@@ -169,7 +168,7 @@ class SetupAll:
         tokenizer.finalize_import(args.config)
 
         LOG.warning('Recompute word counts')
         tokenizer.finalize_import(args.config)
 
         LOG.warning('Recompute word counts')

-        tokenizer.update_statistics()
+        tokenizer.update_statistics(args.config, threads=num_threads)

 
         webdir = args.project_dir / 'website'
         LOG.warning('Setup website at %s', webdir)
 
         webdir = args.project_dir / 'website'
         LOG.warning('Setup website at %s', webdir)


@@ -220,12 +219,11 @@ class SetupAll:
         """ Determine the database date and set the status accordingly.
         """
         with connect(dsn) as conn:
         """ Determine the database date and set the status accordingly.
         """
         with connect(dsn) as conn:

-            if not offline:
-                try:
-                    dbdate = status.compute_database_date(conn)
-                    status.set_status(conn, dbdate)
-                    LOG.info('Database is at %s.', dbdate)
-                except Exception as exc: # pylint: disable=broad-except
-                    LOG.error('Cannot determine date of database: %s', exc)
-

             properties.set_property(conn, 'database_version', str(NOMINATIM_VERSION))
             properties.set_property(conn, 'database_version', str(NOMINATIM_VERSION))

+
+            try:
+                dbdate = status.compute_database_date(conn, offline)
+                status.set_status(conn, dbdate)
+                LOG.info('Database is at %s.', dbdate)
+            except Exception as exc: # pylint: disable=broad-except
+                LOG.error('Cannot determine date of database: %s', exc)