reorganize and complete tests around generic token analysis

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

diff --git a/test/python/test_tokenizer_icu_rule_loader.py b/test/python/test_tokenizer_icu_rule_loader.py
index 4671e0fe323a219e58bd9a977a9fde8e72c32fd4..e22ccd4b054f1a73d3e9bc99b25ba3715356ca38 100644 (file)
--- a/test/python/test_tokenizer_icu_rule_loader.py
+++ b/test/python/test_tokenizer_icu_rule_loader.py
@@ -122,6 +122,15 @@ def test_transliteration_rules_from_file(test_config):
     assert trans.transliterate(" axxt ") == " byt "
 
 
+def test_search_rules(cfgrules):
+    config = cfgrules('~street => s,st', 'master => mstr')
+    proc = ICURuleLoader(config).make_token_analysis()
+
+    assert proc.search.transliterate('Master Street').strip() == 'master street'
+    assert proc.search.transliterate('Earnes St').strip() == 'earnes st'
+    assert proc.search.transliterate('Nostreet').strip() == 'nostreet'
+
+
 class TestGetReplacements:
 
     @pytest.fixture(autouse=True)