reintroduce cutoffs when searching for very frequent words

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

diff --git a/nominatim/clicmd/setup.py b/nominatim/clicmd/setup.py
index fd2c685bd11604f827bc04ac5687cddd5c300c3a..ccd6bd788ed315a45bc8d2e7b2d872bdb64c8de5 100644 (file)
--- a/nominatim/clicmd/setup.py
+++ b/nominatim/clicmd/setup.py
@@ -39,14 +39,15 @@ class SetupAll:
     """
 
     def add_args(self, parser: argparse.ArgumentParser) -> None:
     """
 
     def add_args(self, parser: argparse.ArgumentParser) -> None:

-        group_name = parser.add_argument_group('Required arguments')
-        group1 = group_name.add_mutually_exclusive_group(required=True)
+        group1 = parser.add_argument_group('Required arguments')

         group1.add_argument('--osm-file', metavar='FILE', action='append',
                            help='OSM file to be imported'
         group1.add_argument('--osm-file', metavar='FILE', action='append',
                            help='OSM file to be imported'

-                                ' (repeat for importing multiple files)')
+                                ' (repeat for importing multiple files)',
+                                default=None)

         group1.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=['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)')
         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)')


@@ -65,13 +66,11 @@ class SetupAll:
                            help='Continue import even when errors in SQL are present')
         group3.add_argument('--index-noanalyse', action='store_true',
                            help='Do not perform analyse operations during index (expert only)')
                            help='Continue import even when errors in SQL are present')
         group3.add_argument('--index-noanalyse', action='store_true',
                            help='Do not perform analyse operations during index (expert only)')

-        group3.add_argument('--no-superuser', action='store_true',
-                            help='Do not attempt to create the database')

         group3.add_argument('--prepare-database', action='store_true',
                             help='Create the database but do not import any data')
 
 
         group3.add_argument('--prepare-database', action='store_true',
                             help='Create the database but do not import any data')
 
 

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


@@ -80,23 +79,31 @@ class SetupAll:
 
         country_info.setup_country_config(args.config)
 
 
         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).")
+        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).")

 
 

-            if args.no_superuser and args.prepare_database:
-                raise UsageError("Cannot use --no-superuser and --prepare-database together.")
+        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.")

 
 

-            if args.prepare_database or self.is_complete_import(args):
-                LOG.warning('Creating database')
-                database_import.setup_database_skeleton(args.config.get_libpq_dsn(),
+        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)
                                                         rouser=args.config.DATABASE_WEBUSER)

+            if args.prepare_database:
+                return 0

 
 

-                if not self.is_complete_import(args):
-                    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 not args.prepare_database or args.no_superuser or self.is_complete_import(args):
+            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')
                 # Check if the correct plugins are installed
                 database_import.check_existing_database_plugins(args.config.get_libpq_dsn())
                 LOG.warning('Setting up country tables')


@@ -126,7 +133,7 @@ class SetupAll:
 
                 self._setup_tables(args.config, args.reverse_only)
 
 
                 self._setup_tables(args.config, args.reverse_only)
 

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

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


@@ -137,12 +144,13 @@ class SetupAll:
         LOG.warning("Setting up tokenizer")
         tokenizer = self._get_tokenizer(args.continue_at, args.config)
 
         LOG.warning("Setting up tokenizer")
         tokenizer = self._get_tokenizer(args.continue_at, args.config)
 

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

             LOG.warning('Calculate postcodes')
             postcodes.update_postcodes(args.config.get_libpq_dsn(),
                                        args.project_dir, tokenizer)
 
             LOG.warning('Calculate postcodes')
             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')
             indexer = Indexer(args.config.get_libpq_dsn(), tokenizer, num_threads)
             indexer.index_full(analyse=not args.index_noanalyse)
             LOG.warning('Indexing places')
             indexer = Indexer(args.config.get_libpq_dsn(), tokenizer, num_threads)
             indexer.index_full(analyse=not args.index_noanalyse)


@@ -160,7 +168,7 @@ class SetupAll:
         tokenizer.finalize_import(args.config)
 
         LOG.warning('Recompute word counts')
         tokenizer.finalize_import(args.config)
 
         LOG.warning('Recompute word counts')

-        tokenizer.update_statistics()
+        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)


@@ -170,11 +178,6 @@ class SetupAll:
         self._finalize_database(args.config.get_libpq_dsn(), args.offline)
 
         return 0
         self._finalize_database(args.config.get_libpq_dsn(), args.offline)
 
         return 0

-    
-    def _is_complete_import(self, args: NominatimArgs) -> bool:
-        """ Determine if the import is complete or if only the database should be prepared.
-        """
-        return not args.no_superuser and not args.prepare_database

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


@@ -204,7 +207,7 @@ class SetupAll:
         """
         from ..tokenizer import factory as tokenizer_factory
 
         """
         from ..tokenizer import factory as tokenizer_factory
 

-        if continue_at is None or continue_at == 'load-data':
+        if continue_at in ('import-from-file', 'load-data', None):

             # (re)initialise the tokenizer data
             return tokenizer_factory.create_tokenizer(config)
 
             # (re)initialise the tokenizer data
             return tokenizer_factory.create_tokenizer(config)
 


@@ -216,12 +219,11 @@ class SetupAll:
         """ Determine the database date and set the status accordingly.
         """
         with connect(dsn) as conn:
         """ Determine the database date and set the status accordingly.
         """
         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))
             properties.set_property(conn, 'database_version', str(NOMINATIM_VERSION))

+
+            try:
+                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)