reintroduce cutoffs when searching for very frequent words

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

diff --git a/nominatim/clicmd/index.py b/nominatim/clicmd/index.py
index 8fd4f6011251f480a3d37ff2572d979c7b971cb5..16b5311c79f5764c2f9cde048b5635e0a1619e03 100644 (file)
--- a/nominatim/clicmd/index.py
+++ b/nominatim/clicmd/index.py
@@ -1,10 +1,19 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# This file is part of Nominatim. (https://nominatim.org)
+#
+# Copyright (C) 2022 by the Nominatim developer community.
+# For a full list of authors see the git log.
 """
 Implementation of the 'index' subcommand.
 """
+import argparse
+
 import psutil
 
 from nominatim.db import status
 from nominatim.db.connection import connect
+from nominatim.clicmd.args import NominatimArgs
 
 # Do not repeat documentation of subcommand classes.
 # pylint: disable=C0111
@@ -15,10 +24,14 @@ from nominatim.db.connection import connect
 class UpdateIndex:
     """\
     Reindex all new and modified data.
+
+    Indexing is the process of computing the address and search terms for
+    the places in the database. Every time data is added or changed, indexing
+    needs to be run. Imports and replication updates automatically take care
+    of indexing. For other cases, this function allows to run indexing manually.
     """
 
-    @staticmethod
-    def add_args(parser):
+    def add_args(self, parser: argparse.ArgumentParser) -> None:
         group = parser.add_argument_group('Filter arguments')
         group.add_argument('--boundaries-only', action='store_true',
                            help="""Index only administrative boundaries.""")
@@ -29,11 +42,14 @@ class UpdateIndex:
         group.add_argument('--maxrank', '-R', type=int, metavar='RANK', default=30,
                            help='Maximum/finishing rank')
 
-    @staticmethod
-    def run(args):
+
+    def run(self, args: NominatimArgs) -> int:
         from ..indexer.indexer import Indexer
+        from ..tokenizer import factory as tokenizer_factory
+
+        tokenizer = tokenizer_factory.get_tokenizer_for_db(args.config)
 
-        indexer = Indexer(args.config.get_libpq_dsn(),
+        indexer = Indexer(args.config.get_libpq_dsn(), tokenizer,
                           args.threads or psutil.cpu_count() or 1)
 
         if not args.no_boundaries: