Merge pull request #2357 from lonvia/legacy-tokenizer-fix-word-entries

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

diff --git a/nominatim/clicmd/replication.py b/nominatim/clicmd/replication.py
index fc18945ec854469ac2421117bdc0aea493462c29..242b0f6a0b00c80bacc05ef01b97823e6bed2dfd 100644 (file)
--- a/nominatim/clicmd/replication.py
+++ b/nominatim/clicmd/replication.py
@@ -6,9 +6,9 @@ import logging
 import socket
 import time
 
 import socket
 import time
 

-from ..db import status
-from ..db.connection import connect
-from ..errors import UsageError
+from nominatim.db import status
+from nominatim.db.connection import connect
+from nominatim.errors import UsageError

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


@@ -29,17 +29,17 @@ class UpdateReplication:
                            help='Initialise the update process')
         group.add_argument('--no-update-functions', dest='update_functions',
                            action='store_false',
                            help='Initialise the update process')
         group.add_argument('--no-update-functions', dest='update_functions',
                            action='store_false',

-                           help="""Do not update the trigger function to
-                                   support differential updates.""")
+                           help=("Do not update the trigger function to "
+                                 "support differential updates."))

         group = parser.add_argument_group('Arguments for updates')
         group.add_argument('--check-for-updates', action='store_true',
                            help='Check if new updates are available and exit')
         group.add_argument('--once', action='store_true',
         group = parser.add_argument_group('Arguments for updates')
         group.add_argument('--check-for-updates', action='store_true',
                            help='Check if new updates are available and exit')
         group.add_argument('--once', action='store_true',

-                           help="""Download and apply updates only once. When
-                                   not set, updates are continuously applied""")
+                           help=("Download and apply updates only once. When "
+                                 "not set, updates are continuously applied"))

         group.add_argument('--no-index', action='store_false', dest='do_index',
         group.add_argument('--no-index', action='store_false', dest='do_index',

-                           help="""Do not index the new data. Only applicable
-                                   together with --once""")
+                           help=("Do not index the new data. Only applicable "
+                                 "together with --once"))

         group.add_argument('--osm2pgsql-cache', metavar='SIZE', type=int,
                            help='Size of cache to be used by osm2pgsql (in MB)')
         group = parser.add_argument_group('Download parameters')
         group.add_argument('--osm2pgsql-cache', metavar='SIZE', type=int,
                            help='Size of cache to be used by osm2pgsql (in MB)')
         group = parser.add_argument_group('Download parameters')


@@ -55,8 +55,7 @@ class UpdateReplication:
             replication.init_replication(conn, base_url=args.config.REPLICATION_URL)
             if args.update_functions:
                 LOG.warning("Create functions")
             replication.init_replication(conn, base_url=args.config.REPLICATION_URL)
             if args.update_functions:
                 LOG.warning("Create functions")

-                refresh.create_functions(conn, args.config, args.sqllib_dir,
-                                         True, False)
+                refresh.create_functions(conn, args.config, True, False)

         return 0
 
 
         return 0
 
 


@@ -84,6 +83,7 @@ class UpdateReplication:
     def _update(args):
         from ..tools import replication
         from ..indexer.indexer import Indexer
     def _update(args):
         from ..tools import replication
         from ..indexer.indexer import Indexer

+        from ..tokenizer import factory as tokenizer_factory

 
         params = args.osm2pgsql_options(default_cache=2000, default_threads=1)
         params.update(base_url=args.config.REPLICATION_URL,
 
         params = args.osm2pgsql_options(default_cache=2000, default_threads=1)
         params.update(base_url=args.config.REPLICATION_URL,


@@ -107,6 +107,8 @@ class UpdateReplication:
                 raise UsageError("Bad argument '--no-index'.")
             recheck_interval = args.config.get_int('REPLICATION_RECHECK_INTERVAL')
 
                 raise UsageError("Bad argument '--no-index'.")
             recheck_interval = args.config.get_int('REPLICATION_RECHECK_INTERVAL')
 

+        tokenizer = tokenizer_factory.get_tokenizer_for_db(args.config)
+

         while True:
             with connect(args.config.get_libpq_dsn()) as conn:
                 start = dt.datetime.now(dt.timezone.utc)
         while True:
             with connect(args.config.get_libpq_dsn()) as conn:
                 start = dt.datetime.now(dt.timezone.utc)


@@ -114,10 +116,11 @@ class UpdateReplication:
                 if state is not replication.UpdateState.NO_CHANGES:
                     status.log_status(conn, start, 'import')
                 batchdate, _, _ = status.get_status(conn)
                 if state is not replication.UpdateState.NO_CHANGES:
                     status.log_status(conn, start, 'import')
                 batchdate, _, _ = status.get_status(conn)

+                conn.commit()

 
             if state is not replication.UpdateState.NO_CHANGES and args.do_index:
                 index_start = dt.datetime.now(dt.timezone.utc)
 
             if state is not replication.UpdateState.NO_CHANGES and args.do_index:
                 index_start = dt.datetime.now(dt.timezone.utc)

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

                                   args.threads or 1)
                 indexer.index_boundaries(0, 30)
                 indexer.index_by_rank(0, 30)
                                   args.threads or 1)
                 indexer.index_boundaries(0, 30)
                 indexer.index_by_rank(0, 30)


@@ -125,6 +128,7 @@ class UpdateReplication:
                 with connect(args.config.get_libpq_dsn()) as conn:
                     status.set_indexed(conn, True)
                     status.log_status(conn, index_start, 'index')
                 with connect(args.config.get_libpq_dsn()) as conn:
                     status.set_indexed(conn, True)
                     status.log_status(conn, index_start, 'index')

+                    conn.commit()

             else:
                 index_start = None
 
             else:
                 index_start = None