Merge remote-tracking branch 'upstream/master'

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

diff --git a/nominatim/clicmd/setup.py b/nominatim/clicmd/setup.py
index 27847920b80a434b1f4df0b1b4ac0b7b17ba5b24..8464e151f4f1534034c442446a44bc7c27bce22c 100644 (file)
--- a/nominatim/clicmd/setup.py
+++ b/nominatim/clicmd/setup.py
@@ -1,19 +1,31 @@
+# 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 'import' subcommand.
 """
 """
 Implementation of the 'import' subcommand.
 """

+from typing import Optional
+import argparse

 import logging
 from pathlib import Path
 
 import psutil
 
 import logging
 from pathlib import Path
 
 import psutil
 

+from nominatim.config import Configuration

 from nominatim.db.connection import connect
 from nominatim.db import status, properties
 from nominatim.db.connection import connect
 from nominatim.db import status, properties

+from nominatim.tokenizer.base import AbstractTokenizer

 from nominatim.version import NOMINATIM_VERSION
 from nominatim.version import NOMINATIM_VERSION

+from nominatim.clicmd.args import NominatimArgs
+from nominatim.errors import UsageError

 
 # Do not repeat documentation of subcommand classes.
 # pylint: disable=C0111
 # Using non-top-level imports to avoid eventually unused imports.
 
 # Do not repeat documentation of subcommand classes.
 # pylint: disable=C0111
 # Using non-top-level imports to avoid eventually unused imports.

-# pylint: disable=E0012,C0415
+# pylint: disable=C0415

 
 LOG = logging.getLogger()
 
 
 LOG = logging.getLogger()
 


@@ -26,43 +38,48 @@ class SetupAll:
     needs superuser rights on the database.
     """
 
     needs superuser rights on the database.
     """
 

-    @staticmethod
-    def add_args(parser):
+    def add_args(self, parser: argparse.ArgumentParser) -> None:

         group_name = parser.add_argument_group('Required arguments')
         group_name = parser.add_argument_group('Required arguments')

-        group = group_name.add_mutually_exclusive_group(required=True)
-        group.add_argument('--osm-file', metavar='FILE', action='append',
+        group1 = group_name.add_mutually_exclusive_group(required=True)
+        group1.add_argument('--osm-file', metavar='FILE', action='append',

                            help='OSM file to be imported'
                                 ' (repeat for importing multiple files)')
                            help='OSM file to be imported'
                                 ' (repeat for importing multiple files)')

-        group.add_argument('--continue', dest='continue_at',
+        group1.add_argument('--continue', dest='continue_at',

                            choices=['load-data', 'indexing', 'db-postprocess'],
                            help='Continue an import that was interrupted')
                            choices=['load-data', 'indexing', 'db-postprocess'],
                            help='Continue an import that was interrupted')

-        group = parser.add_argument_group('Optional arguments')
-        group.add_argument('--osm2pgsql-cache', metavar='SIZE', type=int,
+        group2 = parser.add_argument_group('Optional arguments')
+        group2.add_argument('--osm2pgsql-cache', metavar='SIZE', type=int,

                            help='Size of cache to be used by osm2pgsql (in MB)')
                            help='Size of cache to be used by osm2pgsql (in MB)')

-        group.add_argument('--reverse-only', action='store_true',
+        group2.add_argument('--reverse-only', action='store_true',

                            help='Do not create tables and indexes for searching')
                            help='Do not create tables and indexes for searching')

-        group.add_argument('--no-partitions', action='store_true',
+        group2.add_argument('--no-partitions', action='store_true',

                            help=("Do not partition search indices "
                                  "(speeds up import of single country extracts)"))
                            help=("Do not partition search indices "
                                  "(speeds up import of single country extracts)"))

-        group.add_argument('--no-updates', action='store_true',
+        group2.add_argument('--no-updates', action='store_true',

                            help="Do not keep tables that are only needed for "
                                 "updating the database later")
                            help="Do not keep tables that are only needed for "
                                 "updating the database later")

-        group = parser.add_argument_group('Expert options')
-        group.add_argument('--ignore-errors', action='store_true',
+        group2.add_argument('--offline', action='store_true',
+                            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')
                            help='Continue import even when errors in SQL are present')

-        group.add_argument('--index-noanalyse', action='store_true',
+        group3.add_argument('--index-noanalyse', action='store_true',

                            help='Do not perform analyse operations during index (expert only)')
 
 
                            help='Do not perform analyse operations during index (expert only)')
 
 

-    @staticmethod
-    def run(args):
-        from ..tools import database_import, refresh, postcodes, freeze, country_info
+    def run(self, args: NominatimArgs) -> int: # pylint: disable=too-many-statements
+        from ..data import country_info
+        from ..tools import database_import, refresh, postcodes, freeze

         from ..indexer.indexer import Indexer
 
         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:
             files = args.get_osm_file_list()
         country_info.setup_country_config(args.config)
 
         if args.continue_at is None:
             files = args.get_osm_file_list()

+            if not files:
+                raise UsageError("No input files (use --osm-file).")

 
             LOG.warning('Creating database')
             database_import.setup_database_skeleton(args.config.get_libpq_dsn(),
 
             LOG.warning('Creating database')
             database_import.setup_database_skeleton(args.config.get_libpq_dsn(),


@@ -70,7 +87,7 @@ class SetupAll:
 
             LOG.warning('Setting up country tables')
             country_info.setup_country_tables(args.config.get_libpq_dsn(),
 
             LOG.warning('Setting up country tables')
             country_info.setup_country_tables(args.config.get_libpq_dsn(),

-                                              args.data_dir,
+                                              args.config.lib_dir.data,

                                               args.no_partitions)
 
             LOG.warning('Importing OSM data file')
                                               args.no_partitions)
 
             LOG.warning('Importing OSM data file')


@@ -79,14 +96,21 @@ class SetupAll:
                                             drop=args.no_updates,
                                             ignore_errors=args.ignore_errors)
 
                                             drop=args.no_updates,
                                             ignore_errors=args.ignore_errors)
 

-            SetupAll._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. '
             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')
 
         if args.continue_at is None or args.continue_at == 'load-data':
             LOG.warning('Initialise tables')


@@ -94,11 +118,10 @@ class SetupAll:
                 database_import.truncate_data_tables(conn)
 
             LOG.warning('Load data into placex table')
                 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")
 
         LOG.warning("Setting up tokenizer")

-        tokenizer = SetupAll._get_tokenizer(args.continue_at, args.config)
+        tokenizer = self._get_tokenizer(args.continue_at, args.config)

 
         if args.continue_at is None or args.continue_at == 'load-data':
             LOG.warning('Calculate postcodes')
 
         if args.continue_at is None or args.continue_at == 'load-data':
             LOG.warning('Calculate postcodes')


@@ -106,41 +129,36 @@ class SetupAll:
                                        args.project_dir, tokenizer)
 
         if args.continue_at is None or args.continue_at in ('load-data', 'indexing'):
                                        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:
-                    SetupAll._create_pending_index(conn, args.config.TABLESPACE_ADDRESS_INDEX)

             LOG.warning('Indexing places')
             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,
             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,
             LOG.warning('Create search index for default country names.')
             country_info.create_country_names(conn, tokenizer,

-                                              args.config.LANGUAGES)
+                                              args.config.get_str_list('LANGUAGES'))

             if args.no_updates:
                 freeze.drop_update_tables(conn)
         tokenizer.finalize_import(args.config)
 
             if args.no_updates:
                 freeze.drop_update_tables(conn)
         tokenizer.finalize_import(args.config)
 

+        LOG.warning('Recompute word counts')
+        tokenizer.update_statistics()

 
         webdir = args.project_dir / 'website'
         LOG.warning('Setup website at %s', webdir)
         with connect(args.config.get_libpq_dsn()) as conn:
             refresh.setup_website(webdir, args.config, conn)
 
 
         webdir = args.project_dir / 'website'
         LOG.warning('Setup website at %s', webdir)
         with connect(args.config.get_libpq_dsn()) as conn:
             refresh.setup_website(webdir, args.config, conn)
 

-        with connect(args.config.get_libpq_dsn()) as conn:
-            SetupAll._set_database_date(conn)
-            properties.set_property(conn, 'database_version',
-                                    '{0[0]}.{0[1]}.{0[2]}-{0[3]}'.format(NOMINATIM_VERSION))
+        self._finalize_database(args.config.get_libpq_dsn(), args.offline)

 
         return 0
 
 
 
         return 0
 
 

-    @staticmethod
-    def _setup_tables(config, reverse_only):
+    def _setup_tables(self, config: Configuration, reverse_only: bool) -> None:

         """ Set up the basic database layout: tables, indexes and functions.
         """
         from ..tools import database_import, refresh
         """ Set up the basic database layout: tables, indexes and functions.
         """
         from ..tools import database_import, refresh


@@ -161,8 +179,8 @@ class SetupAll:
             refresh.create_functions(conn, config, False, False)
 
 
             refresh.create_functions(conn, config, False, False)
 
 

-    @staticmethod
-    def _get_tokenizer(continue_at, config):
+    def _get_tokenizer(self, continue_at: Optional[str],
+                       config: Configuration) -> AbstractTokenizer:

         """ Set up a new tokenizer or load an already initialised one.
         """
         from ..tokenizer import factory as tokenizer_factory
         """ Set up a new tokenizer or load an already initialised one.
         """
         from ..tokenizer import factory as tokenizer_factory


@@ -174,35 +192,17 @@ class SetupAll:
         # just load the tokenizer
         return tokenizer_factory.get_tokenizer_for_db(config)
 
         # just load the tokenizer
         return tokenizer_factory.get_tokenizer_for_db(config)
 

-    @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()
-
-
-    @staticmethod
-    def _set_database_date(conn):
+    def _finalize_database(self, dsn: str, offline: bool) -> None:

         """ Determine the database date and set the status accordingly.
         """
         """ Determine the database date and set the status accordingly.
         """

-        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)
+        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))