remove country restriction from tokenizer

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

diff --git a/test/python/test_tokenizer_icu_name_processor.py b/test/python/test_tokenizer_icu_name_processor.py
index c1ad767577a67569c10119629e3d3a1df5b2e207..cc1031164c2872b77ed7dcf0fb3600df05895376 100644 (file)
--- a/test/python/test_tokenizer_icu_name_processor.py
+++ b/test/python/test_tokenizer_icu_name_processor.py
@@ -39,23 +39,6 @@ def cfgfile(tmp_path, suffix='.yaml'):
 def get_normalized_variants(proc, name):
     return proc.get_variants_ascii(proc.get_normalized(name))
 
 def get_normalized_variants(proc, name):
     return proc.get_variants_ascii(proc.get_normalized(name))
 

-def test_simple_variants(cfgfile):
-    fpath = cfgfile('~strasse,~straße -> str',
-                    '~weg => weg',
-                    'prospekt -> pr')
-
-    rules = ICUNameProcessorRules(loader=ICURuleLoader(fpath))
-    proc = ICUNameProcessor(rules)
-
-    assert set(get_normalized_variants(proc, "Bauwegstraße")) \
-            == {'bauweg straße', 'bauweg str', 'bauwegstraße', 'bauwegstr'}
-    assert get_normalized_variants(proc, "Bauwegstr") == ['bauwegstr']
-    assert set(get_normalized_variants(proc, "holzweg")) \
-            == {'holz weg', 'holzweg'}
-    assert set(get_normalized_variants(proc, "Meier Weg")) \
-            == {'meier weg', 'meierweg'}
-    assert get_normalized_variants(proc, "hallo") == ['hallo']
-

 
 def test_variants_empty(cfgfile):
     fpath = cfgfile('saint -> 🜵', 'street -> st')
 
 def test_variants_empty(cfgfile):
     fpath = cfgfile('saint -> 🜵', 'street -> st')


@@ -68,15 +51,46 @@ def test_variants_empty(cfgfile):
     assert get_normalized_variants(proc, 'saint') == ['saint']
 
 
     assert get_normalized_variants(proc, 'saint') == ['saint']
 
 

-def test_multiple_replacements(cfgfile):
-    fpath = cfgfile('saint -> s,st', 'street -> st')
-
-    rules = ICUNameProcessorRules(loader=ICURuleLoader(fpath))
-    proc = ICUNameProcessor(rules)
-
-    assert set(get_normalized_variants(proc, "Saint Johns Street")) == \
-            {'saint johns street', 's johns street', 'st johns street',
-             'saint johns st', 's johns st', 'st johns st'}
+VARIANT_TESTS = [
+(('~strasse,~straße -> str', '~weg => weg'), "hallo", {'hallo'}),
+(('weg => wg',), "holzweg", {'holzweg'}),
+(('weg -> wg',), "holzweg", {'holzweg'}),
+(('~weg => weg',), "holzweg", {'holz weg', 'holzweg'}),
+(('~weg -> weg',), "holzweg",  {'holz weg', 'holzweg'}),
+(('~weg => w',), "holzweg", {'holz w', 'holzw'}),
+(('~weg -> w',), "holzweg",  {'holz weg', 'holzweg', 'holz w', 'holzw'}),
+(('~weg => weg',), "Meier Weg", {'meier weg', 'meierweg'}),
+(('~weg -> weg',), "Meier Weg", {'meier weg', 'meierweg'}),
+(('~weg => w',), "Meier Weg", {'meier w', 'meierw'}),
+(('~weg -> w',), "Meier Weg", {'meier weg', 'meierweg', 'meier w', 'meierw'}),
+(('weg => wg',), "Meier Weg", {'meier wg'}),
+(('weg -> wg',), "Meier Weg", {'meier weg', 'meier wg'}),
+(('~strasse,~straße -> str', '~weg => weg'), "Bauwegstraße",
+     {'bauweg straße', 'bauweg str', 'bauwegstraße', 'bauwegstr'}),
+(('am => a', 'bach => b'), "am bach", {'a b'}),
+(('am => a', '~bach => b'), "am bach", {'a b'}),
+(('am -> a', '~bach -> b'), "am bach", {'am bach', 'a bach', 'am b', 'a b'}),
+(('am -> a', '~bach -> b'), "ambach", {'ambach', 'am bach', 'amb', 'am b'}),
+(('saint -> s,st', 'street -> st'), "Saint Johns Street",
+     {'saint johns street', 's johns street', 'st johns street',
+      'saint johns st', 's johns st', 'st johns st'}),
+(('river$ -> r',), "River Bend Road", {'river bend road'}),
+(('river$ -> r',), "Bent River", {'bent river', 'bent r'}),
+(('^north => n',), "North 2nd Street", {'n 2nd street'}),
+(('^north => n',), "Airport North", {'airport north'}),
+(('am -> a',), "am am am am am am am am", {'am am am am am am am am'}),
+(('am => a',), "am am am am am am am am", {'a a a a a a a a'})
+]
+
+@pytest.mark.parametrize("rules,name,variants", VARIANT_TESTS)
+def test_variants(cfgfile, rules, name, variants):
+    fpath = cfgfile(*rules)
+    proc = ICUNameProcessor(ICUNameProcessorRules(loader=ICURuleLoader(fpath)))
+
+    result = get_normalized_variants(proc, name)
+
+    assert len(result) == len(set(result))
+    assert set(get_normalized_variants(proc, name)) == variants

 
 
 def test_search_normalized(cfgfile):
 
 
 def test_search_normalized(cfgfile):