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 ceac7a2421dc43afd23ecc1cf3a4c3066c7b02f1..aa90f8dba02ed3aaf3380362122dcb6029ce1f47 100644 (file)
--- a/test/python/test_tools_database_import.py
+++ b/test/python/test_tools_database_import.py
@@ -1,10 +1,10 @@
 """
 Tests for functions to import a new database.
 """
 """
 Tests for functions to import a new database.
 """

+from pathlib import Path
+

 import pytest
 import psycopg2
 import pytest
 import psycopg2

-import sys
-from pathlib import Path

 
 from nominatim.tools import database_import
 from nominatim.errors import UsageError
 
 from nominatim.tools import database_import
 from nominatim.errors import UsageError


@@ -34,9 +34,9 @@ def test_setup_skeleton(src_dir, nonexistant_db, no_partitions):
     try:
         with conn.cursor() as cur:
             cur.execute("SELECT distinct partition FROM country_name")
     try:
         with conn.cursor() as cur:
             cur.execute("SELECT distinct partition FROM country_name")

-            partitions = set([r[0] for r in list(cur)])
+            partitions = set((r[0] for r in list(cur)))

             if no_partitions:
             if no_partitions:

-                assert partitions == set([0])
+                assert partitions == set((0, ))

             else:
                 assert len(partitions) > 10
     finally:
             else:
                 assert len(partitions) > 10
     finally:


@@ -67,10 +67,11 @@ def test_create_db_missing_ro_user(nonexistant_db):
         database_import.create_db('dbname=' + nonexistant_db, rouser='sdfwkjkjgdugu2;jgsafkljas;')
 
 
         database_import.create_db('dbname=' + nonexistant_db, rouser='sdfwkjkjgdugu2;jgsafkljas;')
 
 

-def test_setup_extensions(temp_db_conn, temp_db_cursor):
+def test_setup_extensions(temp_db_conn, table_factory):

     database_import.setup_extensions(temp_db_conn)
 
     database_import.setup_extensions(temp_db_conn)
 

-    temp_db_cursor.execute('CREATE TABLE t (h HSTORE, geom GEOMETRY(Geometry, 4326))')
+    # Use table creation to check that hstore and geometry types are available.
+    table_factory('t', 'h HSTORE, geom GEOMETRY(Geometry, 4326)')

 
 
 def test_setup_extensions_old_postgis(temp_db_conn, monkeypatch):
 
 
 def test_setup_extensions_old_postgis(temp_db_conn, monkeypatch):


@@ -80,57 +81,61 @@ def test_setup_extensions_old_postgis(temp_db_conn, monkeypatch):
         database_import.setup_extensions(temp_db_conn)
 
 
         database_import.setup_extensions(temp_db_conn)
 
 

-def test_import_base_data(src_dir, temp_db, temp_db_cursor):
-    temp_db_cursor.execute('CREATE EXTENSION hstore')
-    temp_db_cursor.execute('CREATE EXTENSION postgis')
-    database_import.import_base_data('dbname=' + temp_db, src_dir / 'data')
+def test_import_base_data(dsn, src_dir, temp_db_with_extensions, temp_db_cursor):
+    database_import.import_base_data(dsn, src_dir / 'data')
+
+    assert temp_db_cursor.table_rows('country_name') > 0

 
 

-    assert temp_db_cursor.scalar('SELECT count(*) FROM country_name') > 0

 
 

+def test_import_base_data_ignore_partitions(dsn, src_dir, temp_db_with_extensions,
+                                            temp_db_cursor):
+    database_import.import_base_data(dsn, src_dir / 'data', ignore_partitions=True)

 
 

-def test_import_base_data_ignore_partitions(src_dir, temp_db, temp_db_cursor):
-    temp_db_cursor.execute('CREATE EXTENSION hstore')
-    temp_db_cursor.execute('CREATE EXTENSION postgis')
-    database_import.import_base_data('dbname=' + temp_db, src_dir / 'data',
-                                     ignore_partitions=True)
+    assert temp_db_cursor.table_rows('country_name') > 0
+    assert temp_db_cursor.table_rows('country_name', where='partition != 0') == 0

 
 

-    assert temp_db_cursor.scalar('SELECT count(*) FROM country_name') > 0
-    assert temp_db_cursor.scalar('SELECT count(*) FROM country_name WHERE partition != 0') == 0

 
 

+def test_import_osm_data_simple(table_factory, osm2pgsql_options):
+    table_factory('place', content=((1, ), ))
+
+    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

 
 

-def test_import_osm_data_simple(temp_db_cursor,osm2pgsql_options):
-    temp_db_cursor.execute('CREATE TABLE place (id INT)')
-    temp_db_cursor.execute('INSERT INTO place values (1)')
+    files = [tmp_path / 'file1.osm', tmp_path / 'file2.osm']
+    for f in files:
+        f.write_text('test')

 
 

-    database_import.import_osm_data('file.pdf', osm2pgsql_options)
+    database_import.import_osm_data(files, osm2pgsql_options)

 
 
 
 

-def test_import_osm_data_simple_no_data(temp_db_cursor,osm2pgsql_options):
-    temp_db_cursor.execute('CREATE TABLE place (id INT)')
+def test_import_osm_data_simple_no_data(table_factory, osm2pgsql_options):
+    table_factory('place')

 
     with pytest.raises(UsageError, match='No data.*'):
 
     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(temp_db_conn, temp_db_cursor, tmp_path, osm2pgsql_options):
-    temp_db_cursor.execute('CREATE TABLE place (id INT)')
-    temp_db_cursor.execute('CREATE TABLE planet_osm_nodes (id INT)')
-    temp_db_cursor.execute('INSERT INTO place values (1)')
+def test_import_osm_data_drop(table_factory, temp_db_conn, tmp_path, osm2pgsql_options):
+    table_factory('place', content=((1, ), ))
+    table_factory('planet_osm_nodes')

 
     flatfile = tmp_path / 'flatfile'
     flatfile.write_text('touch')
 
     osm2pgsql_options['flatnode_file'] = str(flatfile.resolve())
 
 
     flatfile = tmp_path / 'flatfile'
     flatfile.write_text('touch')
 
     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')
 
 
 
     assert not flatfile.exists()
     assert not temp_db_conn.table_exists('planet_osm_nodes')
 
 

-def test_import_osm_data_default_cache(temp_db_cursor,osm2pgsql_options):
-    temp_db_cursor.execute('CREATE TABLE place (id INT)')
-    temp_db_cursor.execute('INSERT INTO place values (1)')
+def test_import_osm_data_default_cache(table_factory, osm2pgsql_options):
+    table_factory('place', content=((1, ), ))

 
     osm2pgsql_options['osm2pgsql_cache'] = 0
 
 
     osm2pgsql_options['osm2pgsql_cache'] = 0
 


@@ -153,8 +158,8 @@ def test_truncate_database_tables(temp_db_conn, temp_db_cursor, table_factory):
 
 
 @pytest.mark.parametrize("threads", (1, 5))
 
 
 @pytest.mark.parametrize("threads", (1, 5))

-def test_load_data(dsn, src_dir, place_row, placex_table, osmline_table, word_table,
-                   temp_db_cursor, threads):
+def test_load_data(dsn, place_row, placex_table, osmline_table,
+                   word_table, temp_db_cursor, threads):

     for func in ('precompute_words', 'getorcreate_housenumber_id', 'make_standard_name'):
         temp_db_cursor.execute("""CREATE FUNCTION {} (src TEXT)
                                   RETURNS TEXT AS $$ SELECT 'a'::TEXT $$ LANGUAGE SQL
     for func in ('precompute_words', 'getorcreate_housenumber_id', 'make_standard_name'):
         temp_db_cursor.execute("""CREATE FUNCTION {} (src TEXT)
                                   RETURNS TEXT AS $$ SELECT 'a'::TEXT $$ LANGUAGE SQL


@@ -186,7 +191,7 @@ def test_create_country_names(temp_db_with_extensions, temp_db_conn, temp_db_cur
 
     assert len(tokenizer.analyser_cache['countries']) == 2
 
 
     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')),
 
     if languages:
         assert result_set == {'us' : set(('us', 'us1', 'United States')),