"""
Implementation of the 'import' subcommand.
"""
+from typing import Optional
+import argparse
import logging
from pathlib import Path
import psutil
+from nominatim.config import Configuration
from nominatim.db.connection import connect
from nominatim.db import status, properties
+from nominatim.tokenizer.base import AbstractTokenizer
from nominatim.version import NOMINATIM_VERSION
+from nominatim.clicmd.args import NominatimArgs
+from nominatim.errors import UsageError
# Do not repeat documentation of subcommand classes.
# pylint: disable=C0111
# Using non-top-level imports to avoid eventually unused imports.
-# pylint: disable=E0012,C0415
+# pylint: disable=C0415
LOG = logging.getLogger()
needs superuser rights on the database.
"""
- @staticmethod
- def add_args(parser):
- group_name = parser.add_argument_group('Required arguments')
- group = group_name.add_mutually_exclusive_group(required=True)
- group.add_argument('--osm-file', metavar='FILE', action='append',
+ def add_args(self, parser: argparse.ArgumentParser) -> None:
+ 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)')
- group.add_argument('--continue', dest='continue_at',
- choices=['load-data', 'indexing', 'db-postprocess'],
- help='Continue an import that was interrupted')
- group = parser.add_argument_group('Optional arguments')
- group.add_argument('--osm2pgsql-cache', metavar='SIZE', type=int,
+ ' (repeat for importing multiple files)',
+ default=None)
+ group1.add_argument('--continue', dest='continue_at',
+ 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)')
- group.add_argument('--reverse-only', action='store_true',
+ group2.add_argument('--reverse-only', action='store_true',
help='Do not create tables and indexes for searching')
- group.add_argument('--no-partitions', action='store_true',
+ group2.add_argument('--no-partitions', action='store_true',
help=("Do not partition search indices "
"(speeds up import of single country extracts)"))
- group.add_argument('--no-updates', action='store_true',
+ group2.add_argument('--no-updates', action='store_true',
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',
+ group2.add_argument('--offline', action='store_true',
+ help="Do not attempt to load any additional data from the internet")
+ group3 = parser.add_argument_group('Expert options')
+ group3.add_argument('--ignore-errors', action='store_true',
help='Continue import even when errors in SQL are present')
- group.add_argument('--index-noanalyse', action='store_true',
+ group3.add_argument('--index-noanalyse', action='store_true',
help='Do not perform analyse operations during index (expert only)')
+ group3.add_argument('--prepare-database', action='store_true',
+ help='Create the database but do not import any data')
- @staticmethod
- def run(args):
- from ..tools import database_import, refresh, postcodes, freeze, country_info
+ 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
- country_info.setup_country_config(args.config)
+ num_threads = args.threads or psutil.cpu_count() or 1
- if args.continue_at is None:
- files = args.get_osm_file_list()
+ country_info.setup_country_config(args.config)
- LOG.warning('Creating database')
- database_import.setup_database_skeleton(args.config.get_libpq_dsn(),
- rouser=args.config.DATABASE_WEBUSER)
+ 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).")
- LOG.warning('Setting up country tables')
- country_info.setup_country_tables(args.config.get_libpq_dsn(),
- args.data_dir,
- args.no_partitions)
+ 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.")
- LOG.warning('Importing OSM data file')
- database_import.import_osm_data(files,
- args.osm2pgsql_options(0, 1),
- drop=args.no_updates,
- ignore_errors=args.ignore_errors)
+ if args.continue_at is not None and args.prepare_database:
+ raise UsageError(
+ "Cannot use --continue and --prepare-database together."
+ )
- SetupAll._setup_tables(args.config, args.reverse_only)
- LOG.warning('Importing wikipedia importance data')
- data_path = Path(args.config.WIKIPEDIA_DATA_PATH or args.project_dir)
- if refresh.import_wikipedia_articles(args.config.get_libpq_dsn(),
- data_path) > 0:
- LOG.error('Wikipedia importance dump file not found. '
- 'Will be using default importances.')
+ 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 is None or args.continue_at == 'load-data':
+ 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 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')
+ country_info.setup_country_tables(args.config.get_libpq_dsn(),
+ args.config.lib_dir.data,
+ args.no_partitions)
+
+ LOG.warning('Importing OSM data file')
+ database_import.import_osm_data(files,
+ args.osm2pgsql_options(0, 1),
+ drop=args.no_updates,
+ ignore_errors=args.ignore_errors)
+
+ LOG.warning('Importing wikipedia importance data')
+ data_path = Path(args.config.WIKIPEDIA_DATA_PATH or args.project_dir)
+ if refresh.import_wikipedia_articles(args.config.get_libpq_dsn(),
+ data_path) > 0:
+ LOG.error('Wikipedia importance dump file not found. '
+ 'Calculating importance values of locations will not '
+ 'use Wikipedia importance data.')
+
+ LOG.warning('Importing secondary importance raster data')
+ if refresh.import_secondary_importance(args.config.get_libpq_dsn(),
+ args.project_dir) != 0:
+ LOG.error('Secondary importance file not imported. '
+ 'Falling back to default ranking.')
+
+ self._setup_tables(args.config, args.reverse_only)
+
+ 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('Load data into placex table')
- database_import.load_data(args.config.get_libpq_dsn(),
- args.threads or psutil.cpu_count() or 1)
+ database_import.load_data(args.config.get_libpq_dsn(), num_threads)
LOG.warning("Setting up tokenizer")
- tokenizer = SetupAll._get_tokenizer(args.continue_at, args.config)
+ 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)
- 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)
+ if args.continue_at in \
+ ('import-from-file', 'load-data', 'indexing', None):
LOG.warning('Indexing places')
- indexer = Indexer(args.config.get_libpq_dsn(), tokenizer,
- args.threads or psutil.cpu_count() or 1)
+ indexer = Indexer(args.config.get_libpq_dsn(), tokenizer, num_threads)
indexer.index_full(analyse=not args.index_noanalyse)
LOG.warning('Post-process tables')
with connect(args.config.get_libpq_dsn()) as conn:
database_import.create_search_indices(conn, args.config,
- drop=args.no_updates)
+ drop=args.no_updates,
+ threads=num_threads)
LOG.warning('Create search index for default country names.')
country_info.create_country_names(conn, tokenizer,
- args.config.LANGUAGES)
+ args.config.get_str_list('LANGUAGES'))
if args.no_updates:
freeze.drop_update_tables(conn)
tokenizer.finalize_import(args.config)
LOG.warning('Recompute word counts')
- tokenizer.update_statistics()
+ tokenizer.update_statistics(args.config)
webdir = args.project_dir / 'website'
LOG.warning('Setup website at %s', webdir)
with connect(args.config.get_libpq_dsn()) as conn:
refresh.setup_website(webdir, args.config, conn)
- SetupAll._set_database_date(args.config.get_libpq_dsn())
+ self._finalize_database(args.config.get_libpq_dsn(), args.offline)
return 0
- @staticmethod
- def _setup_tables(config, reverse_only):
+ def _setup_tables(self, config: Configuration, reverse_only: bool) -> None:
""" Set up the basic database layout: tables, indexes and functions.
"""
from ..tools import database_import, refresh
refresh.create_functions(conn, config, False, False)
- @staticmethod
- def _get_tokenizer(continue_at, config):
+ def _get_tokenizer(self, continue_at: Optional[str],
+ config: Configuration) -> AbstractTokenizer:
""" Set up a new tokenizer or load an already initialised one.
"""
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)
# just load the tokenizer
return tokenizer_factory.get_tokenizer_for_db(config)
- @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()
-
-
- @staticmethod
- def _set_database_date(dsn):
+ def _finalize_database(self, dsn: str, offline: bool) -> None:
""" Determine the database date and set the status accordingly.
"""
with connect(dsn) as conn:
+ properties.set_property(conn, 'database_version', str(NOMINATIM_VERSION))
+
try:
- dbdate = status.compute_database_date(conn)
+ 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)
-
- properties.set_property(conn, 'database_version',
- '{0[0]}.{0[1]}.{0[2]}-{0[3]}'.format(NOMINATIM_VERSION))
projects / nominatim.git / blobdiff