reintroduce cutoffs when searching for very frequent words

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

diff --git a/nominatim/clicmd/refresh.py b/nominatim/clicmd/refresh.py
index ecc7498eff7ef0b448a274e8158171f593ccedd7..343fe48d204468ce495f8340db1285391096e81b 100644 (file)
--- a/nominatim/clicmd/refresh.py
+++ b/nominatim/clicmd/refresh.py
@@ -7,11 +7,15 @@
 """
 Implementation of 'refresh' subcommand.
 """
-from argparse import ArgumentTypeError
+from typing import Tuple, Optional
+import argparse
 import logging
 from pathlib import Path
 
+from nominatim.config import Configuration
 from nominatim.db.connection import connect
+from nominatim.tokenizer.base import AbstractTokenizer
+from nominatim.clicmd.args import NominatimArgs
 
 # Do not repeat documentation of subcommand classes.
 # pylint: disable=C0111
@@ -20,12 +24,12 @@ from nominatim.db.connection import connect
 
 LOG = logging.getLogger()
 
-def _parse_osm_object(obj):
+def _parse_osm_object(obj: str) -> Tuple[str, int]:
     """ Parse the given argument into a tuple of OSM type and ID.
         Raises an ArgumentError if the format is not recognized.
     """
     if len(obj) < 2 or obj[0].lower() not in 'nrw' or not obj[1:].isdigit():
-        raise ArgumentTypeError("Cannot parse OSM ID. Expect format: [N|W|R]<id>.")
+        raise argparse.ArgumentTypeError("Cannot parse OSM ID. Expect format: [N|W|R]<id>.")
 
     return (obj[0].upper(), int(obj[1:]))
 
@@ -42,11 +46,10 @@ class UpdateRefresh:
     Warning: the 'update' command must not be run in parallel with other update
              commands like 'replication' or 'add-data'.
     """
-    def __init__(self):
-        self.tokenizer = None
+    def __init__(self) -> None:
+        self.tokenizer: Optional[AbstractTokenizer] = None
 
-    @staticmethod
-    def add_args(parser):
+    def add_args(self, parser: argparse.ArgumentParser) -> None:
         group = parser.add_argument_group('Data arguments')
         group.add_argument('--postcodes', action='store_true',
                            help='Update postcode centroid table')
@@ -60,6 +63,8 @@ class UpdateRefresh:
                            help='Update the PL/pgSQL functions in the database')
         group.add_argument('--wiki-data', action='store_true',
                            help='Update Wikipedia/data importance numbers')
+        group.add_argument('--secondary-importance', action='store_true',
+                           help='Update secondary importance raster data')
         group.add_argument('--importance', action='store_true',
                            help='Recompute place importances (expensive!)')
         group.add_argument('--website', action='store_true',
@@ -80,7 +85,7 @@ class UpdateRefresh:
                            help='Enable debug warning statements in functions')
 
 
-    def run(self, args): #pylint: disable=too-many-branches
+    def run(self, args: NominatimArgs) -> int: #pylint: disable=too-many-branches, too-many-statements
         from ..tools import refresh, postcodes
         from ..indexer.indexer import Indexer
 
@@ -105,13 +110,28 @@ class UpdateRefresh:
 
         if args.word_counts:
             LOG.warning('Recompute word statistics')
-            self._get_tokenizer(args.config).update_statistics()
+            self._get_tokenizer(args.config).update_statistics(args.config,
+                                                               threads=args.threads or 1)
 
         if args.address_levels:
             LOG.warning('Updating address levels')
             with connect(args.config.get_libpq_dsn()) as conn:
                 refresh.load_address_levels_from_config(conn, args.config)
 
+        # Attention: must come BEFORE functions
+        if args.secondary_importance:
+            with connect(args.config.get_libpq_dsn()) as conn:
+                # If the table did not exist before, then the importance code
+                # needs to be enabled.
+                if not conn.table_exists('secondary_importance'):
+                    args.functions = True
+
+            LOG.warning('Import secondary importance raster data from %s', args.project_dir)
+            if refresh.import_secondary_importance(args.config.get_libpq_dsn(),
+                                                args.project_dir) > 0:
+                LOG.fatal('FATAL: Cannot update secondary importance raster data')
+                return 1
+
         if args.functions:
             LOG.warning('Create functions')
             with connect(args.config.get_libpq_dsn()) as conn:
@@ -122,10 +142,10 @@ class UpdateRefresh:
         if args.wiki_data:
             data_path = Path(args.config.WIKIPEDIA_DATA_PATH
                              or args.project_dir)
-            LOG.warning('Import wikipdia article importance from %s', data_path)
+            LOG.warning('Import wikipedia article importance from %s', data_path)
             if refresh.import_wikipedia_articles(args.config.get_libpq_dsn(),
                                                  data_path) > 0:
-                LOG.fatal('FATAL: Wikipedia importance dump file not found')
+                LOG.fatal('FATAL: Wikipedia importance file not found in %s', data_path)
                 return 1
 
         # Attention: importance MUST come after wiki data import.
@@ -155,7 +175,7 @@ class UpdateRefresh:
         return 0
 
 
-    def _get_tokenizer(self, config):
+    def _get_tokenizer(self, config: Configuration) -> AbstractTokenizer:
         if self.tokenizer is None:
             from ..tokenizer import factory as tokenizer_factory