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 754f3b2f9d4f3b28e19a21ce6194c643490edcb3..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:
-        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)',
@@ -71,7 +70,7 @@ class SetupAll:
                             help='Create the database but do not import any data')
 
 
-    def run(self, args: NominatimArgs) -> int: # pylint: disable=too-many-statements
+    def run(self, args: NominatimArgs) -> int: # pylint: disable=too-many-statements, too-many-branches
         from ..data import country_info
         from ..tools import database_import, refresh, postcodes, freeze
         from ..indexer.indexer import Indexer
@@ -80,8 +79,7 @@ class SetupAll:
 
         country_info.setup_country_config(args.config)
 
-        # Check if osm-file or continue_at is set, if both are set, or none are set, throw an error
-        if args.osm_file is None and args.continue_at is None:
+        if args.osm_file is None and args.continue_at is None and not args.prepare_database:
             raise UsageError("No input files (use --osm-file).")
 
         if args.osm_file is not None and args.continue_at not in ('import-from-file', None):
@@ -93,18 +91,18 @@ class SetupAll:
             )
 
 
+        if args.prepare_database or args.continue_at is None:
+            LOG.warning('Creating database')
+            database_import.setup_database_skeleton(args.config.get_libpq_dsn(),
+                                                        rouser=args.config.DATABASE_WEBUSER)
+            if args.prepare_database:
+                return 0
 
         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.prepare_database or args.continue_at is None:
-                LOG.warning('Creating database')
-                database_import.setup_database_skeleton(args.config.get_libpq_dsn(),
-                                                        rouser=args.config.DATABASE_WEBUSER)
-                return 0
-
             if args.continue_at in ('import-from-file', None):
                 # Check if the correct plugins are installed
                 database_import.check_existing_database_plugins(args.config.get_libpq_dsn())
@@ -170,7 +168,7 @@ class SetupAll:
         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)
@@ -209,7 +207,7 @@ class SetupAll:
         """
         from ..tokenizer import factory as tokenizer_factory
 
-        if continue_at is None or continue_at == 'load-data':
+        if continue_at in ('import-from-file', 'load-data', None):
             # (re)initialise the tokenizer data
             return tokenizer_factory.create_tokenizer(config)
 
@@ -221,12 +219,11 @@ class SetupAll:
         """ 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))
+
+            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)