import psutil
-from ..tools.exec_utils import run_legacy_script
-from ..db.connection import connect
-from ..db import status, properties
-from ..version import NOMINATIM_VERSION
-from ..errors import UsageError
+from nominatim.db.connection import connect
+from nominatim.db import status, properties
+from nominatim.version import NOMINATIM_VERSION
+from nominatim.errors import UsageError
# Do not repeat documentation of subcommand classes.
# pylint: disable=C0111
group.add_argument('--reverse-only', action='store_true',
help='Do not create tables and indexes for searching')
group.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',
- 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',
help='Continue import even when errors in SQL are present')
@staticmethod
def run(args): # pylint: disable=too-many-statements
- from ..tools import database_import
- from ..tools import refresh
+ from ..tools import database_import, refresh, postcodes, freeze
from ..indexer.indexer import Indexer
+ from ..tokenizer import factory as tokenizer_factory
if args.osm_file and not Path(args.osm_file).is_file():
LOG.fatal("OSM file '%s' does not exist.", args.osm_file)
args.no_partitions,
rouser=args.config.DATABASE_WEBUSER)
- 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)
-
LOG.warning('Importing OSM data file')
database_import.import_osm_data(Path(args.osm_file),
args.osm2pgsql_options(0, 1),
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)
+ refresh.create_functions(conn, args.config, False, False)
LOG.warning('Create tables')
- database_import.create_tables(conn, args.config, args.sqllib_dir,
+ database_import.create_tables(conn, args.config,
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)
+ refresh.create_functions(conn, args.config, False, False)
LOG.warning('Create table triggers')
- database_import.create_table_triggers(conn, args.config, args.sqllib_dir)
+ database_import.create_table_triggers(conn, args.config)
LOG.warning('Create partition tables')
- database_import.create_partition_tables(conn, args.config, args.sqllib_dir)
+ database_import.create_partition_tables(conn, args.config)
LOG.warning('Create functions (3rd pass)')
- refresh.create_functions(conn, args.config, args.sqllib_dir,
- False, False)
+ refresh.create_functions(conn, args.config, False, False)
LOG.warning('Importing wikipedia importance data')
data_path = Path(args.config.WIKIPEDIA_DATA_PATH or args.project_dir)
LOG.error('Wikipedia importance dump file not found. '
'Will be using default importances.')
+ if args.continue_at is None or args.continue_at == 'load-data':
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')
database_import.load_data(args.config.get_libpq_dsn(),
- args.data_dir,
args.threads or psutil.cpu_count() or 1)
+ LOG.warning("Setting up tokenizer")
+ if args.continue_at is None or args.continue_at == 'load-data':
+ # (re)initialise the tokenizer data
+ tokenizer = tokenizer_factory.create_tokenizer(args.config)
+ else:
+ # just load the tokenizer
+ tokenizer = tokenizer_factory.get_tokenizer_for_db(args.config)
+
+ if args.continue_at is None or args.continue_at == 'load-data':
LOG.warning('Calculate postcodes')
- run_legacy_script('setup.php', '--calculate-postcodes',
- nominatim_env=args, throw_on_fail=not args.ignore_errors)
+ 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 is not None and args.continue_at != 'load-data':
+ with connect(args.config.get_libpq_dsn()) as conn:
+ SetupAll._create_pending_index(conn, args.config.TABLESPACE_ADDRESS_INDEX)
LOG.warning('Indexing places')
- indexer = Indexer(args.config.get_libpq_dsn(),
+ indexer = Indexer(args.config.get_libpq_dsn(), tokenizer,
args.threads or psutil.cpu_count() or 1)
indexer.index_full(analyse=not args.index_noanalyse)
LOG.warning('Post-process tables')
- params = ['setup.php', '--create-search-indices', '--create-country-names']
- if args.no_updates:
- params.append('--drop')
- run_legacy_script(*params, nominatim_env=args, throw_on_fail=not args.ignore_errors)
+ with connect(args.config.get_libpq_dsn()) as conn:
+ database_import.create_search_indices(conn, args.config,
+ drop=args.no_updates)
+ LOG.warning('Create search index for default country names.')
+ database_import.create_country_names(conn, tokenizer,
+ args.config.LANGUAGES)
+ conn.commit()
+ if args.no_updates:
+ freeze.drop_update_tables(conn)
+ tokenizer.finalize_import(args.config)
+
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:
+ refresh.setup_website(webdir, args.config, conn)
with connect(args.config.get_libpq_dsn()) as conn:
try:
'{0[0]}.{0[1]}.{0[2]}-{0[3]}'.format(NOMINATIM_VERSION))
return 0
+
+
+ @staticmethod
+ def _create_pending_index(conn, tablespace):
+ """ Add a supporting index for finding places still to be indexed.
+
+ This index is normally created at the end of the import process
+ for later updates. When indexing was partially done, then this
+ index can greatly improve speed going through already indexed data.
+ """
+ if conn.index_exists('idx_placex_pendingsector'):
+ return
+
+ with conn.cursor() as cur:
+ LOG.warning('Creating support index')
+ if tablespace:
+ tablespace = 'TABLESPACE ' + tablespace
+ cur.execute("""CREATE INDEX idx_placex_pendingsector
+ ON placex USING BTREE (rank_address,geometry_sector)
+ {} WHERE indexed_status > 0
+ """.format(tablespace))
+ conn.commit()
projects / nominatim.git / blobdiff