remove country restriction from tokenizer

[nominatim.git] / test / python / test_tools_database_import.py

diff --git a/test/python/test_tools_database_import.py b/test/python/test_tools_database_import.py
index 621610cf6b248cf01faac8660d1cd1bebdb308d4..aa90f8dba02ed3aaf3380362122dcb6029ce1f47 100644 (file)
--- a/test/python/test_tools_database_import.py
+++ b/test/python/test_tools_database_import.py
@@ -98,14 +98,25 @@ def test_import_base_data_ignore_partitions(dsn, src_dir, temp_db_with_extension
 def test_import_osm_data_simple(table_factory, osm2pgsql_options):
     table_factory('place', content=((1, ), ))
 
-    database_import.import_osm_data('file.pdf', osm2pgsql_options)
+    database_import.import_osm_data(Path('file.pbf'), osm2pgsql_options)
+
+
+def test_import_osm_data_multifile(table_factory, tmp_path, osm2pgsql_options):
+    table_factory('place', content=((1, ), ))
+    osm2pgsql_options['osm2pgsql_cache'] = 0
+
+    files = [tmp_path / 'file1.osm', tmp_path / 'file2.osm']
+    for f in files:
+        f.write_text('test')
+
+    database_import.import_osm_data(files, osm2pgsql_options)
 
 
 def test_import_osm_data_simple_no_data(table_factory, osm2pgsql_options):
     table_factory('place')
 
     with pytest.raises(UsageError, match='No data.*'):
-        database_import.import_osm_data('file.pdf', osm2pgsql_options)
+        database_import.import_osm_data(Path('file.pbf'), osm2pgsql_options)
 
 
 def test_import_osm_data_drop(table_factory, temp_db_conn, tmp_path, osm2pgsql_options):
@@ -117,7 +128,7 @@ def test_import_osm_data_drop(table_factory, temp_db_conn, tmp_path, osm2pgsql_o
 
     osm2pgsql_options['flatnode_file'] = str(flatfile.resolve())
 
-    database_import.import_osm_data('file.pdf', osm2pgsql_options, drop=True)
+    database_import.import_osm_data(Path('file.pbf'), osm2pgsql_options, drop=True)
 
     assert not flatfile.exists()
     assert not temp_db_conn.table_exists('planet_osm_nodes')
@@ -180,7 +191,7 @@ def test_create_country_names(temp_db_with_extensions, temp_db_conn, temp_db_cur
 
     assert len(tokenizer.analyser_cache['countries']) == 2
 
-    result_set = {k: set(v) for k, v in tokenizer.analyser_cache['countries']}
+    result_set = {k: set(v.values()) for k, v in tokenizer.analyser_cache['countries']}
 
     if languages:
         assert result_set == {'us' : set(('us', 'us1', 'United States')),