Merge pull request #2450 from mtmail/tiger-data-2021

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

diff --git a/nominatim/tools/country_info.py b/nominatim/tools/country_info.py
index 49cf7286237abe9aaf2f0081b2e96f2a9324ed55..635d15840a84b8197efb9f5cb358344a78a0c2b9 100644 (file)
--- a/nominatim/tools/country_info.py
+++ b/nominatim/tools/country_info.py
@@ -1,9 +1,56 @@
 """
 Functions for importing and managing static country information.
 """
+import psycopg2.extras
+
 from nominatim.db import utils as db_utils
 from nominatim.db.connection import connect
 
+class _CountryInfo:
+    """ Caches country-specific properties from the configuration file.
+    """
+
+    def __init__(self):
+        self._info = {}
+
+
+    def load(self, config):
+        """ Load the country properties from the configuration files,
+            if they are not loaded yet.
+        """
+        if not self._info:
+            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(',')]
+
+
+    def items(self):
+        """ Return tuples of (country_code, property dict) as iterable.
+        """
+        return self._info.items()
+
+
+_COUNTRY_INFO = _CountryInfo()
+
+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(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.
@@ -11,8 +58,56 @@ def setup_country_tables(dsn, sql_dir, ignore_partitions=False):
     db_utils.execute_file(dsn, sql_dir / 'country_name.sql')
     db_utils.execute_file(dsn, sql_dir / 'country_osm_grid.sql.gz')
 
-    if ignore_partitions:
-        with connect(dsn) as conn:
-            with conn.cursor() as cur:
-                cur.execute('UPDATE country_name SET partition = 0')
-            conn.commit()
+    params = []
+    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')
+            lang = props['languages'][0] if len(props['languages']) == 1 else None
+            params.append((ccode, partition, lang))
+
+    with connect(dsn) as conn:
+        with conn.cursor() as cur:
+            cur.execute_values(
+                """ UPDATE country_name
+                    SET partition = part, country_default_language_code = lang
+                    FROM (VALUES %s) AS v (cc, part, lang)
+                    WHERE country_code = v.cc""", params)
+        conn.commit()
+
+
+def create_country_names(conn, tokenizer, languages=None):
+    """ Add default country names to search index. `languages` is a comma-
+        separated list of language codes as used in OSM. If `languages` is not
+        empty then only name translations for the given languages are added
+        to the index.
+    """
+    if languages:
+        languages = languages.split(',')
+
+    def _include_key(key):
+        return key == 'name' or \
+               (key.startswith('name:') and (not languages or key[5:] in languages))
+
+    with conn.cursor() as cur:
+        psycopg2.extras.register_hstore(cur)
+        cur.execute("""SELECT country_code, name FROM country_name
+                       WHERE country_code is not null""")
+
+        with tokenizer.name_analyzer() as analyzer:
+            for code, name in cur:
+                names = {'countrycode': code}
+                if code == 'gb':
+                    names['short_name'] = 'UK'
+                if code == 'us':
+                    names['short_name'] = 'United States'
+
+                # country names (only in languages as provided)
+                if name:
+                    names.update(((k, v) for k, v in name.items() if _include_key(k)))
+
+                analyzer.add_country_names(code, names)
+
+    conn.commit()