reintroduce 'name:' prefix to country name keys

[nominatim.git] / nominatim / tools / country_info.py

diff --git a/nominatim/tools/country_info.py b/nominatim/tools/country_info.py
index 1f7b799610743926f513f67fe3e40b20e76e6397..69697434cba9a79f20786b6ebd932945b206c17a 100644 (file)
--- a/nominatim/tools/country_info.py
+++ b/nominatim/tools/country_info.py
@@ -1,11 +1,18 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# This file is part of Nominatim. (https://nominatim.org)
+#
+# Copyright (C) 2022 by the Nominatim developer community.
+# For a full list of authors see the git log.
 """
 Functions for importing and managing static country information.
 """
+import json
 import psycopg2.extras
-import yaml
 
 from nominatim.db import utils as db_utils
 from nominatim.db.connection import connect
+from io import StringIO
 
 class _CountryInfo:
     """ Caches country-specific properties from the configuration file.
@@ -14,47 +21,76 @@ class _CountryInfo:
     def __init__(self):
         self._info = {}
 
-    def load(self, configfile):
+
+    def load(self, config):
+        """ Load the country properties from the configuration files,
+            if they are not loaded yet.
+        """
         if not self._info:
-            self._info = yaml.safe_load(configfile.read_text())
+            self._info = config.load_sub_configuration('country_settings.yaml')
+            # Convert languages into a list for simpler handling.
+            for prop in self._info.values():
+                if 'languages' not in prop:
+                    prop['languages'] = []
+                elif not isinstance(prop['languages'], list):
+                    prop['languages'] = [x.strip()
+                                         for x in prop['languages'].split(',')]
+                if 'name' not in prop:
+                    prop['name'] = {}
 
     def items(self):
+        """ Return tuples of (country_code, property dict) as iterable.
+        """
         return self._info.items()
 
 
 _COUNTRY_INFO = _CountryInfo()
 
-def setup_country_config(configfile):
+def setup_country_config(config):
     """ Load country properties from the configuration file.
         Needs to be called before using any other functions in this
         file.
     """
-    _COUNTRY_INFO.load(configfile)
-    print(_COUNTRY_INFO._info)
+    _COUNTRY_INFO.load(config)
+
+
+def iterate():
+    """ Iterate over country code and properties.
+    """
+    return _COUNTRY_INFO.items()
 
 
 def setup_country_tables(dsn, sql_dir, ignore_partitions=False):
     """ Create and populate the tables with basic static data that provides
         the background for geocoding. Data is assumed to not yet exist.
     """
-    db_utils.execute_file(dsn, sql_dir / 'country_name.sql')
     db_utils.execute_file(dsn, sql_dir / 'country_osm_grid.sql.gz')
 
-    params = []
+    params, country_names_data = [], ''
     for ccode, props in _COUNTRY_INFO.items():
         if ccode is not None and props is not None:
             if ignore_partitions:
                 partition = 0
             else:
                 partition = props.get('partition')
-            if ',' in (props.get('languages', ',') or ','):
-                lang = None
-            else:
-                lang = props['languages']
+            lang = props['languages'][0] if len(props['languages']) == 1 else None
             params.append((ccode, partition, lang))
 
+            name = json.dumps(props.get('name'), ensure_ascii=False, separators=(', ', '=>'))
+            country_names_data += ccode + '\t' + name[1:-1] + '\n'
+
     with connect(dsn) as conn:
         with conn.cursor() as cur:
+            cur.execute(
+                """CREATE TABLE public.country_name (
+                        country_code character varying(2),
+                        name public.hstore,
+                        derived_name public.hstore,
+                        country_default_language_code text,
+                        partition integer
+                );""")
+            data = StringIO(country_names_data)
+            cur.copy_from(data, 'country_name', columns=('country_code', 'name'))
             cur.execute_values(
                 """ UPDATE country_name
                     SET partition = part, country_default_language_code = lang