adapt tests for new word count mechanism

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

diff --git a/test/python/test_tokenizer_icu.py b/test/python/test_tokenizer_icu.py
index 16caf3edf12299cfe95e57bf5c72e889a39d0c63..4d029dec6b1725553faf32d075a01f3f00010d85 100644 (file)
--- a/test/python/test_tokenizer_icu.py
+++ b/test/python/test_tokenizer_icu.py
@@ -72,7 +72,8 @@ def analyzer(tokenizer_factory, test_config, monkeypatch,
         cfgstr = {'normalization': list(norm),
                   'sanitizers': sanitizers,
                   'transliteration': list(trans),
-                  'token-analysis': [{'variants': [{'words': list(variants)}]}]}
+                  'token-analysis': [{'analyzer': 'generic',
+                                      'variants': [{'words': list(variants)}]}]}
         (test_config.project_dir / 'icu_tokenizer.yaml').write_text(yaml.dump(cfgstr))
         tok.loader = ICURuleLoader(test_config)
 
@@ -159,7 +160,7 @@ def test_init_new(tokenizer_factory, test_config, monkeypatch, db_prop):
     assert db_prop(icu_tokenizer.DBCFG_TERM_NORMALIZATION) == ':: lower();'
 
 
-def test_init_word_table(tokenizer_factory, test_config, place_row, word_table):
+def test_init_word_table(tokenizer_factory, test_config, place_row, temp_db_cursor):
     place_row(names={'name' : 'Test Area', 'ref' : '52'})
     place_row(names={'name' : 'No Area'})
     place_row(names={'name' : 'Holzstrasse'})
@@ -167,10 +168,7 @@ def test_init_word_table(tokenizer_factory, test_config, place_row, word_table):
     tok = tokenizer_factory()
     tok.init_new_db(test_config)
 
-    assert word_table.get_partial_words() == {('test', 1),
-                                              ('no', 1), ('area', 2),
-                                              ('holz', 1), ('strasse', 1),
-                                              ('str', 1)}
+    assert temp_db_cursor.table_exists('word')
 
 
 def test_init_from_project(monkeypatch, test_config, tokenizer_factory):