simplify use of secondary importance

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

diff --git a/nominatim/clicmd/setup.py b/nominatim/clicmd/setup.py
index 6ffa7afb8babb91c58d7f40c0af16cfbb32f110d..344167bb595577256ef691d0e291beafb0c8f252 100644 (file)
--- a/nominatim/clicmd/setup.py
+++ b/nominatim/clicmd/setup.py
@@ -15,7 +15,7 @@ from pathlib import Path
 import psutil
 
 from nominatim.config import Configuration
-from nominatim.db.connection import connect, Connection
+from nominatim.db.connection import connect
 from nominatim.db import status, properties
 from nominatim.tokenizer.base import AbstractTokenizer
 from nominatim.version import version_str
@@ -59,7 +59,7 @@ class SetupAll:
                            help="Do not keep tables that are only needed for "
                                 "updating the database later")
         group2.add_argument('--offline', action='store_true',
-                           help="Do not attempt to load any additional data from the internet")
+                            help="Do not attempt to load any additional data from the internet")
         group3 = parser.add_argument_group('Expert options')
         group3.add_argument('--ignore-errors', action='store_true',
                            help='Continue import even when errors in SQL are present')
@@ -72,6 +72,8 @@ class SetupAll:
         from ..tools import database_import, refresh, postcodes, freeze
         from ..indexer.indexer import Indexer
 
+        num_threads = args.threads or psutil.cpu_count() or 1
+
         country_info.setup_country_config(args.config)
 
         if args.continue_at is None:
@@ -94,14 +96,21 @@ class SetupAll:
                                             drop=args.no_updates,
                                             ignore_errors=args.ignore_errors)
 
-            self._setup_tables(args.config, args.reverse_only)
-
             LOG.warning('Importing wikipedia importance data')
             data_path = Path(args.config.WIKIPEDIA_DATA_PATH or args.project_dir)
             if refresh.import_wikipedia_articles(args.config.get_libpq_dsn(),
                                                  data_path) > 0:
                 LOG.error('Wikipedia importance dump file not found. '
-                          'Will be using default importances.')
+                          'Calculating importance values of locations will not '
+                          'use Wikipedia importance data.')
+
+            LOG.warning('Importing secondary importance raster data')
+            if refresh.import_secondary_importance(args.config.get_libpq_dsn(),
+                                                   args.project_dir) != 0:
+                LOG.error('Secondary importance file not imported. '
+                          'Falling back to default ranking.')
+
+            self._setup_tables(args.config, args.reverse_only)
 
         if args.continue_at is None or args.continue_at == 'load-data':
             LOG.warning('Initialise tables')
@@ -109,8 +118,7 @@ class SetupAll:
                 database_import.truncate_data_tables(conn)
 
             LOG.warning('Load data into placex table')
-            database_import.load_data(args.config.get_libpq_dsn(),
-                                      args.threads or psutil.cpu_count() or 1)
+            database_import.load_data(args.config.get_libpq_dsn(), num_threads)
 
         LOG.warning("Setting up tokenizer")
         tokenizer = self._get_tokenizer(args.continue_at, args.config)
@@ -121,18 +129,15 @@ class SetupAll:
                                        args.project_dir, tokenizer)
 
         if args.continue_at is None or args.continue_at in ('load-data', 'indexing'):
-            if args.continue_at is not None and args.continue_at != 'load-data':
-                with connect(args.config.get_libpq_dsn()) as conn:
-                    self._create_pending_index(conn, args.config.TABLESPACE_ADDRESS_INDEX)
             LOG.warning('Indexing places')
-            indexer = Indexer(args.config.get_libpq_dsn(), tokenizer,
-                              args.threads or psutil.cpu_count() or 1)
+            indexer = Indexer(args.config.get_libpq_dsn(), tokenizer, num_threads)
             indexer.index_full(analyse=not args.index_noanalyse)
 
         LOG.warning('Post-process tables')
         with connect(args.config.get_libpq_dsn()) as conn:
             database_import.create_search_indices(conn, args.config,
-                                                  drop=args.no_updates)
+                                                  drop=args.no_updates,
+                                                  threads=num_threads)
             LOG.warning('Create search index for default country names.')
             country_info.create_country_names(conn, tokenizer,
                                               args.config.get_str_list('LANGUAGES'))
@@ -188,27 +193,6 @@ class SetupAll:
         return tokenizer_factory.get_tokenizer_for_db(config)
 
 
-    def _create_pending_index(self, conn: Connection, tablespace: str) -> None:
-        """ Add a supporting index for finding places still to be indexed.
-
-            This index is normally created at the end of the import process
-            for later updates. When indexing was partially done, then this
-            index can greatly improve speed going through already indexed data.
-        """
-        if conn.index_exists('idx_placex_pendingsector'):
-            return
-
-        with conn.cursor() as cur:
-            LOG.warning('Creating support index')
-            if tablespace:
-                tablespace = 'TABLESPACE ' + tablespace
-            cur.execute(f"""CREATE INDEX idx_placex_pendingsector
-                            ON placex USING BTREE (rank_address,geometry_sector)
-                            {tablespace} WHERE indexed_status > 0
-                         """)
-        conn.commit()
-
-
     def _finalize_database(self, dsn: str, offline: bool) -> None:
         """ Determine the database date and set the status accordingly.
         """