add japanese sanitizer

[nominatim.git] / test / python / tokenizer / sanitizers / test_split_name_list.py

diff --git a/test/python/tokenizer/sanitizers/test_split_name_list.py b/test/python/tokenizer/sanitizers/test_split_name_list.py
index 47bd1e44cb0806ac6c331bced65e7219d90660d5..9ca539d57cb529cac93283c813c3f0a7075900a8 100644 (file)
--- a/test/python/tokenizer/sanitizers/test_split_name_list.py
+++ b/test/python/tokenizer/sanitizers/test_split_name_list.py
@@ -10,62 +10,70 @@ Tests for the sanitizer that splits multivalue lists.
 import pytest
 
 from nominatim.tokenizer.place_sanitizer import PlaceSanitizer
-from nominatim.indexer.place_info import PlaceInfo
+from nominatim.data.place_info import PlaceInfo
 
 from nominatim.errors import UsageError
 
-def run_sanitizer_on(**kwargs):
-    place = PlaceInfo({'name': kwargs})
-    name, _ = PlaceSanitizer([{'step': 'split-name-list'}]).process_names(place)
+class TestSplitName:
 
-    return sorted([(p.name, p.kind, p.suffix) for p in name])
+    @pytest.fixture(autouse=True)
+    def setup_country(self, def_config):
+        self.config = def_config
 
 
-def sanitize_with_delimiter(delimiter, name):
-    place = PlaceInfo({'name': {'name': name}})
-    san = PlaceSanitizer([{'step': 'split-name-list', 'delimiters': delimiter}])
-    name, _ = san.process_names(place)
+    def run_sanitizer_on(self, **kwargs):
+        place = PlaceInfo({'name': kwargs})
+        name, _ = PlaceSanitizer([{'step': 'split-name-list'}], self.config).process_names(place)
 
-    return sorted([p.name for p in name])
+        return sorted([(p.name, p.kind, p.suffix) for p in name])
 
 
-def test_simple():
-    assert run_sanitizer_on(name='ABC') == [('ABC', 'name', None)]
-    assert run_sanitizer_on(name='') == [('', 'name', None)]
+    def sanitize_with_delimiter(self, delimiter, name):
+        place = PlaceInfo({'name': {'name': name}})
+        san = PlaceSanitizer([{'step': 'split-name-list', 'delimiters': delimiter}],
+                             self.config)
+        name, _ = san.process_names(place)
 
+        return sorted([p.name for p in name])
 
-def test_splits():
-    assert run_sanitizer_on(name='A;B;C') == [('A', 'name', None),
-                                              ('B', 'name', None),
-                                              ('C', 'name', None)]
-    assert run_sanitizer_on(short_name=' House, boat ') == [('House', 'short_name', None),
-                                                            ('boat', 'short_name', None)]
 
+    def test_simple(self):
+        assert self.run_sanitizer_on(name='ABC') == [('ABC', 'name', None)]
+        assert self.run_sanitizer_on(name='') == [('', 'name', None)]
 
-def test_empty_fields():
-    assert run_sanitizer_on(name='A;;B') == [('A', 'name', None),
-                                             ('B', 'name', None)]
-    assert run_sanitizer_on(name='A; ,B') == [('A', 'name', None),
-                                              ('B', 'name', None)]
-    assert run_sanitizer_on(name=' ;B') == [('B', 'name', None)]
-    assert run_sanitizer_on(name='B,') == [('B', 'name', None)]
 
+    def test_splits(self):
+        assert self.run_sanitizer_on(name='A;B;C') == [('A', 'name', None),
+                                                       ('B', 'name', None),
+                                                       ('C', 'name', None)]
+        assert self.run_sanitizer_on(short_name=' House, boat ') == [('House', 'short_name', None),
+                                                                     ('boat', 'short_name', None)]
 
-def test_custom_delimiters():
-    assert sanitize_with_delimiter(':', '12:45,3') == ['12', '45,3']
-    assert sanitize_with_delimiter('\\', 'a;\\b!#@ \\') == ['a;', 'b!#@']
-    assert sanitize_with_delimiter('[]', 'foo[to]be') == ['be', 'foo', 'to']
-    assert sanitize_with_delimiter(' ', 'morning  sun') == ['morning', 'sun']
 
+    def test_empty_fields(self):
+        assert self.run_sanitizer_on(name='A;;B') == [('A', 'name', None),
+                                                      ('B', 'name', None)]
+        assert self.run_sanitizer_on(name='A; ,B') == [('A', 'name', None),
+                                                       ('B', 'name', None)]
+        assert self.run_sanitizer_on(name=' ;B') == [('B', 'name', None)]
+        assert self.run_sanitizer_on(name='B,') == [('B', 'name', None)]
 
-def test_empty_delimiter_set():
-    with pytest.raises(UsageError):
-        sanitize_with_delimiter('', 'abc')
 
+    def test_custom_delimiters(self):
+        assert self.sanitize_with_delimiter(':', '12:45,3') == ['12', '45,3']
+        assert self.sanitize_with_delimiter('\\', 'a;\\b!#@ \\') == ['a;', 'b!#@']
+        assert self.sanitize_with_delimiter('[]', 'foo[to]be') == ['be', 'foo', 'to']
+        assert self.sanitize_with_delimiter(' ', 'morning  sun') == ['morning', 'sun']
 
-def test_no_name_list():
+
+    def test_empty_delimiter_set(self):
+        with pytest.raises(UsageError):
+            self.sanitize_with_delimiter('', 'abc')
+
+
+def test_no_name_list(def_config):
     place = PlaceInfo({'address': {'housenumber': '3'}})
-    name, address = PlaceSanitizer([{'step': 'split-name-list'}]).process_names(place)
+    name, address = PlaceSanitizer([{'step': 'split-name-list'}], def_config).process_names(place)
 
     assert not name
     assert len(address) == 1