add full tokens to addresses

[nominatim.git] / test / python / tokenizer / test_icu.py

diff --git a/test/python/tokenizer/test_icu.py b/test/python/tokenizer/test_icu.py
index aa1afe160ca9010630b7b36502d14b173a453003..2a4865db2acb95e4e177c5732441ef1f7dc610a0 100644 (file)
--- a/test/python/tokenizer/test_icu.py
+++ b/test/python/tokenizer/test_icu.py
@@ -227,16 +227,20 @@ def test_update_statistics_reverse_only(word_table, tokenizer_factory, test_conf
 def test_update_statistics(word_table, table_factory, temp_db_cursor,
                            tokenizer_factory, test_config):
     word_table.add_full_word(1000, 'hello')
 def test_update_statistics(word_table, table_factory, temp_db_cursor,
                            tokenizer_factory, test_config):
     word_table.add_full_word(1000, 'hello')

+    word_table.add_full_word(1001, 'bye')

     table_factory('search_name',
     table_factory('search_name',

-                  'place_id BIGINT, name_vector INT[]',
-                  [(12, [1000])])
+                  'place_id BIGINT, name_vector INT[], nameaddress_vector INT[]',
+                  [(12, [1000], [1001])])

     tok = tokenizer_factory()
 
     tok.update_statistics(test_config)
 
     assert temp_db_cursor.scalar("""SELECT count(*) FROM word
     tok = tokenizer_factory()
 
     tok.update_statistics(test_config)
 
     assert temp_db_cursor.scalar("""SELECT count(*) FROM word

-                                    WHERE type = 'W' and
-                                          (info->>'count')::int > 0""") > 0
+                                    WHERE type = 'W' and word_id = 1000 and
+                                          (info->>'count')::int > 0""") == 1
+    assert temp_db_cursor.scalar("""SELECT count(*) FROM word
+                                    WHERE type = 'W' and word_id = 1001 and
+                                          (info->>'addr_count')::int > 0""") == 1

 
 
 def test_normalize_postcode(analyzer):
 
 
 def test_normalize_postcode(analyzer):


@@ -550,7 +554,7 @@ class TestPlaceAddress:
     def test_process_place_place(self):
         info = self.process_address(place='Honu Lulu')
 
     def test_process_place_place(self):
         info = self.process_address(place='Honu Lulu')
 

-        assert eval(info['place']) == self.name_token_set('HONU', 'LULU')
+        assert eval(info['place']) == self.name_token_set('HONU', 'LULU', '#HONU LULU')

 
 
     def test_process_place_place_extra(self):
 
 
     def test_process_place_place_extra(self):


@@ -570,8 +574,8 @@ class TestPlaceAddress:
                                     suburb='Zwickau', street='Hauptstr',
                                     full='right behind the church')
 
                                     suburb='Zwickau', street='Hauptstr',
                                     full='right behind the church')
 

-        city = self.name_token_set('ZWICKAU')
-        state = self.name_token_set('SACHSEN')
+        city = self.name_token_set('ZWICKAU', '#ZWICKAU')
+        state = self.name_token_set('SACHSEN', '#SACHSEN')

 
         result = {k: eval(v) for k,v in info['addr'].items()}
 
 
         result = {k: eval(v) for k,v in info['addr'].items()}
 


@@ -583,7 +587,7 @@ class TestPlaceAddress:
 
         result = {k: eval(v) for k,v in info['addr'].items()}
 
 
         result = {k: eval(v) for k,v in info['addr'].items()}
 

-        assert result == {'city': self.name_token_set('Bruxelles')}
+        assert result == {'city': self.name_token_set('Bruxelles', '#Bruxelles')}

 
 
     def test_process_place_address_terms_empty(self):
 
 
     def test_process_place_address_terms_empty(self):