minimum counts for tokens should always be 1

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

diff --git a/nominatim/clicmd/setup.py b/nominatim/clicmd/setup.py
index fe7c8dc18de4ee650e7bbb42824c813f4e2d9753..ccd6bd788ed315a45bc8d2e7b2d872bdb64c8de5 100644 (file)
--- a/nominatim/clicmd/setup.py
+++ b/nominatim/clicmd/setup.py
@@ -1,150 +1,229 @@
+# 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.
 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.

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

 
 LOG = logging.getLogger()
 
 class SetupAll:
     """\
     Create a new Nominatim database from an OSM file.
 
 LOG = logging.getLogger()
 
 class SetupAll:
     """\
     Create a new Nominatim database from an OSM file.

+
+    This sub-command sets up a new Nominatim database from scratch starting
+    with creating a new database in Postgresql. The user running this command
+    needs superuser rights on the database.

     """
 
     """
 

-    @staticmethod
-    def add_args(parser):
-        group_name = parser.add_argument_group('Required arguments')
-        group = group_name.add_mutually_exclusive_group(required=True)
-        group.add_argument('--osm-file', metavar='FILE',
-                           help='OSM file to be imported.')
-        group.add_argument('--continue', dest='continue_at',
-                           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,
+    def add_args(self, parser: argparse.ArgumentParser) -> None:
+        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)',
+                                default=None)
+        group1.add_argument('--continue', dest='continue_at',
+                           choices=['import-from-file', 'load-data', 'indexing', 'db-postprocess'],
+                           help='Continue an import that was interrupted',
+                           default=None)
+        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',
-                           help='Do not perform analyse operations during index')
+        group3.add_argument('--index-noanalyse', action='store_true',
+                           help='Do not perform analyse operations during index (expert only)')
+        group3.add_argument('--prepare-database', action='store_true',
+                            help='Create the database but do not import any data')

 
 
 
 

-    @staticmethod
-    def run(args): # pylint: disable=too-many-statements
-        from ..tools import database_import
-        from ..tools import refresh
+    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
         from ..indexer.indexer import Indexer

-        from ..tools import postcodes

 
 

-        if args.osm_file and not Path(args.osm_file).is_file():
-            LOG.fatal("OSM file '%s' does not exist.", args.osm_file)
-            raise UsageError('Cannot access file.')
+        num_threads = args.threads or psutil.cpu_count() or 1

 
 

-        if args.continue_at is None:
-            database_import.setup_database_skeleton(args.config.get_libpq_dsn(),
-                                                    args.data_dir,
-                                                    args.no_partitions,
-                                                    rouser=args.config.DATABASE_WEBUSER)
+        country_info.setup_country_config(args.config)

 
 

-            LOG.warning('Installing database module')
-            with connect(args.config.get_libpq_dsn()) as conn:
-                database_import.install_module(args.module_dir, args.project_dir,
-                                               args.config.DATABASE_MODULE_PATH,
-                                               conn=conn)
+        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).")

 
 

-            LOG.warning('Importing OSM data file')
-            database_import.import_osm_data(Path(args.osm_file),
-                                            args.osm2pgsql_options(0, 1),
-                                            drop=args.no_updates,
-                                            ignore_errors=args.ignore_errors)
+        if args.osm_file is not None and args.continue_at not in ('import-from-file', None):
+            raise UsageError(f"Cannot use --continue {args.continue_at} and --osm-file together.")

 
 

-            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)
-                LOG.warning('Create tables')
-                database_import.create_tables(conn, args.config, args.sqllib_dir,
-                                              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)
-                LOG.warning('Create table triggers')
-                database_import.create_table_triggers(conn, args.config, args.sqllib_dir)
-                LOG.warning('Create partition tables')
-                database_import.create_partition_tables(conn, args.config, args.sqllib_dir)
-                LOG.warning('Create functions (3rd pass)')
-                refresh.create_functions(conn, args.config, args.sqllib_dir,
-                                         False, False)
-
-            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.')
+        if args.continue_at is not None and args.prepare_database:
+            raise UsageError(
+                "Cannot use --continue and --prepare-database together."
+            )

 
 

+
+        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:
+                raise UsageError("No input files (use --osm-file).")
+
+            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())
+                LOG.warning('Setting up country tables')
+                country_info.setup_country_tables(args.config.get_libpq_dsn(),
+                                                args.config.lib_dir.data,
+                                                args.no_partitions)
+
+                LOG.warning('Importing OSM data file')
+                database_import.import_osm_data(files,
+                                                args.osm2pgsql_options(0, 1),
+                                                drop=args.no_updates,
+                                                ignore_errors=args.ignore_errors)
+
+                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. '
+                            '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 in ('import-from-file', 'load-data', None):

             LOG.warning('Initialise tables')
             with connect(args.config.get_libpq_dsn()) as conn:
             LOG.warning('Initialise tables')
             with connect(args.config.get_libpq_dsn()) as conn:

-                database_import.truncate_data_tables(conn, args.config.MAX_WORD_FREQUENCY)
+                database_import.truncate_data_tables(conn)

 
 

-        if args.continue_at is None or args.continue_at == 'load-data':

             LOG.warning('Load data into placex table')
             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)
+            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)

 
 

+        if args.continue_at in ('import-from-file', 'load-data', None):

             LOG.warning('Calculate postcodes')
             LOG.warning('Calculate postcodes')

-            postcodes.import_postcodes(args.config.get_libpq_dsn(), args.project_dir)
+            postcodes.update_postcodes(args.config.get_libpq_dsn(),
+                                       args.project_dir, tokenizer)

 
 

-        if args.continue_at is None or args.continue_at in ('load-data', 'indexing'):
+        if args.continue_at in \
+            ('import-from-file', 'load-data', 'indexing', None):

             LOG.warning('Indexing places')
             LOG.warning('Indexing places')

-            indexer = Indexer(args.config.get_libpq_dsn(),
-                              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,

-                                                  args.sqllib_dir,
-                                                  drop=args.no_updates)
+                                                  drop=args.no_updates,
+                                                  threads=num_threads)

             LOG.warning('Create search index for default country names.')
             LOG.warning('Create search index for default country names.')

-            database_import.create_country_names(conn, args.config)
+            country_info.create_country_names(conn, tokenizer,
+                                              args.config.get_str_list('LANGUAGES'))
+            if args.no_updates:
+                freeze.drop_update_tables(conn)
+        tokenizer.finalize_import(args.config)
+
+        LOG.warning('Recompute word counts')
+        tokenizer.update_statistics(args.config, threads=num_threads)

 
         webdir = args.project_dir / 'website'
         LOG.warning('Setup website at %s', webdir)
 
         webdir = args.project_dir / 'website'
         LOG.warning('Setup website at %s', webdir)

-        refresh.setup_website(webdir, args.phplib_dir, args.config)
-

         with connect(args.config.get_libpq_dsn()) as conn:
         with connect(args.config.get_libpq_dsn()) as conn:

+            refresh.setup_website(webdir, args.config, conn)
+
+        self._finalize_database(args.config.get_libpq_dsn(), args.offline)
+
+        return 0
+
+
+    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
+
+        with connect(config.get_libpq_dsn()) as conn:
+            LOG.warning('Create functions (1st pass)')
+            refresh.create_functions(conn, config, False, False)
+            LOG.warning('Create tables')
+            database_import.create_tables(conn, config, reverse_only=reverse_only)
+            refresh.load_address_levels_from_config(conn, config)
+            LOG.warning('Create functions (2nd pass)')
+            refresh.create_functions(conn, config, False, False)
+            LOG.warning('Create table triggers')
+            database_import.create_table_triggers(conn, config)
+            LOG.warning('Create partition tables')
+            database_import.create_partition_tables(conn, config)
+            LOG.warning('Create functions (3rd pass)')
+            refresh.create_functions(conn, config, False, False)
+
+
+    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
+
+        if continue_at in ('import-from-file', 'load-data', None):
+            # (re)initialise the tokenizer data
+            return tokenizer_factory.create_tokenizer(config)
+
+        # just load the tokenizer
+        return tokenizer_factory.get_tokenizer_for_db(config)
+
+
+    def _finalize_database(self, dsn: str, offline: bool) -> None:
+        """ Determine the database date and set the status accordingly.
+        """
+        with connect(dsn) as conn:
+            properties.set_property(conn, 'database_version', str(NOMINATIM_VERSION))
+

             try:
             try:

-                dbdate = status.compute_database_date(conn)
+                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)
                 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',
-                                    '{0[0]}.{0[1]}.{0[2]}-{0[3]}'.format(NOMINATIM_VERSION))
-
-        return 0