introduce tokenizer modules

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

diff --git a/nominatim/clicmd/setup.py b/nominatim/clicmd/setup.py
index 100fdf6747cbe814b401a45d6531c79d161ff81a..687279726a303036e43f08beea8f50529fe7393e 100644 (file)
--- a/nominatim/clicmd/setup.py
+++ b/nominatim/clicmd/setup.py
@@ -6,7 +6,6 @@ from pathlib import Path
 
 import psutil
 
-from nominatim.tools.exec_utils import run_legacy_script
 from nominatim.db.connection import connect
 from nominatim.db import status, properties
 from nominatim.version import NOMINATIM_VERSION
@@ -56,6 +55,8 @@ class SetupAll:
         from ..tools import database_import
         from ..tools import refresh
         from ..indexer.indexer import Indexer
+        from ..tools import postcodes
+        from ..tokenizer import factory as tokenizer_factory
 
         if args.osm_file and not Path(args.osm_file).is_file():
             LOG.fatal("OSM file '%s' does not exist.", args.osm_file)
@@ -81,22 +82,19 @@ class SetupAll:
 
             with connect(args.config.get_libpq_dsn()) as conn:
                 LOG.warning('Create functions (1st pass)')
-                refresh.create_functions(conn, args.config, args.sqllib_dir,
-                                         False, False)
+                refresh.create_functions(conn, args.config, False, False)
                 LOG.warning('Create tables')
-                database_import.create_tables(conn, args.config, args.sqllib_dir,
+                database_import.create_tables(conn, args.config,
                                               reverse_only=args.reverse_only)
                 refresh.load_address_levels_from_file(conn, Path(args.config.ADDRESS_LEVEL_CONFIG))
                 LOG.warning('Create functions (2nd pass)')
-                refresh.create_functions(conn, args.config, args.sqllib_dir,
-                                         False, False)
+                refresh.create_functions(conn, args.config, False, False)
                 LOG.warning('Create table triggers')
-                database_import.create_table_triggers(conn, args.config, args.sqllib_dir)
+                database_import.create_table_triggers(conn, args.config)
                 LOG.warning('Create partition tables')
-                database_import.create_partition_tables(conn, args.config, args.sqllib_dir)
+                database_import.create_partition_tables(conn, args.config)
                 LOG.warning('Create functions (3rd pass)')
-                refresh.create_functions(conn, args.config, args.sqllib_dir,
-                                         False, False)
+                refresh.create_functions(conn, args.config, False, False)
 
             LOG.warning('Importing wikipedia importance data')
             data_path = Path(args.config.WIKIPEDIA_DATA_PATH or args.project_dir)
@@ -105,21 +103,27 @@ class SetupAll:
                 LOG.error('Wikipedia importance dump file not found. '
                           'Will be using default importances.')
 
+        if args.continue_at is None or args.continue_at == 'load-data':
             LOG.warning('Initialise tables')
             with connect(args.config.get_libpq_dsn()) as conn:
                 database_import.truncate_data_tables(conn, args.config.MAX_WORD_FREQUENCY)
 
-        if args.continue_at is None or args.continue_at == 'load-data':
             LOG.warning('Load data into placex table')
             database_import.load_data(args.config.get_libpq_dsn(),
                                       args.data_dir,
                                       args.threads or psutil.cpu_count() or 1)
 
+        LOG.warning("Setting up tokenizer")
+        tokenizer = tokenizer_factory.create_tokenizer(args.config)
+
+        if args.continue_at is None or args.continue_at == 'load-data':
             LOG.warning('Calculate postcodes')
-            run_legacy_script('setup.php', '--calculate-postcodes',
-                              nominatim_env=args, throw_on_fail=not args.ignore_errors)
+            postcodes.import_postcodes(args.config.get_libpq_dsn(), args.project_dir)
 
         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:
+                    SetupAll._create_pending_index(conn, args.config.TABLESPACE_ADDRESS_INDEX)
             LOG.warning('Indexing places')
             indexer = Indexer(args.config.get_libpq_dsn(),
                               args.threads or psutil.cpu_count() or 1)
@@ -128,14 +132,13 @@ class SetupAll:
         LOG.warning('Post-process tables')
         with connect(args.config.get_libpq_dsn()) as conn:
             database_import.create_search_indices(conn, args.config,
-                                                  args.sqllib_dir,
                                                   drop=args.no_updates)
             LOG.warning('Create search index for default country names.')
             database_import.create_country_names(conn, args.config)
 
         webdir = args.project_dir / 'website'
         LOG.warning('Setup website at %s', webdir)
-        refresh.setup_website(webdir, args.phplib_dir, args.config)
+        refresh.setup_website(webdir, args.config)
 
         with connect(args.config.get_libpq_dsn()) as conn:
             try:
@@ -149,3 +152,25 @@ class SetupAll:
                                     '{0[0]}.{0[1]}.{0[2]}-{0[3]}'.format(NOMINATIM_VERSION))
 
         return 0
+
+
+    @staticmethod
+    def _create_pending_index(conn, tablespace):
+        """ 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("""CREATE INDEX idx_placex_pendingsector
+                           ON placex USING BTREE (rank_address,geometry_sector)
+                           {} WHERE indexed_status > 0
+                        """.format(tablespace))
+        conn.commit()