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 9ae812e85bb52e39b57002aa053a56828b0a8022..ccd6bd788ed315a45bc8d2e7b2d872bdb64c8de5 100644 (file)
--- a/nominatim/clicmd/setup.py
+++ b/nominatim/clicmd/setup.py
@@ -39,8 +39,7 @@ 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_argument_group()
+        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)',
         group1.add_argument('--osm-file', metavar='FILE', action='append',
                            help='OSM file to be imported'
                                 ' (repeat for importing multiple files)',


@@ -71,7 +70,7 @@ class SetupAll:
                             help='Create the database but do not import any data')
 
 
                             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


@@ -80,8 +79,7 @@ class SetupAll:
 
         country_info.setup_country_config(args.config)
 
 
         country_info.setup_country_config(args.config)
 

-        # Check if osm-file or continue_at is set, if both are set, or none are set, throw an error
-        if args.osm_file is None and args.continue_at is None:
+        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.osm_file is not None and args.continue_at not in ('import-from-file', None):
             raise UsageError("No input files (use --osm-file).")
 
         if args.osm_file is not None and args.continue_at not in ('import-from-file', None):


@@ -93,23 +91,19 @@ class SetupAll:
             )
 
 
             )
 
 

+        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 args.continue_at in (None, 'import-from-file'):
             files = args.get_osm_file_list()

-            if not files and not args.prepare_database:
+            if not files:

                 raise UsageError("No input files (use --osm-file).")
 
                 raise UsageError("No input files (use --osm-file).")
 

-            if args.prepare_database or self._is_complete_import(args):
-                LOG.warning('Creating database')
-                database_import.setup_database_skeleton(args.config.get_libpq_dsn(),
-                                                        rouser=args.config.DATABASE_WEBUSER)
-
-                if not self._is_complete_import(args):
-                    return 0
-
-            if not args.prepare_database or \
-                    args.continue_at == 'import-from-file' 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')


@@ -139,7 +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 in ('import-from-file', '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)


@@ -174,7 +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)


@@ -185,11 +179,6 @@ class SetupAll:
 
         return 0
 
 
         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 args.continue_at is None and not args.prepare_database
-

 
     def _setup_tables(self, config: Configuration, reverse_only: bool) -> None:
         """ Set up the basic database layout: tables, indexes and functions.
 
     def _setup_tables(self, config: Configuration, reverse_only: bool) -> None:
         """ Set up the basic database layout: tables, indexes and functions.


@@ -218,7 +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)
 


@@ -230,12 +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)