Merge remote-tracking branch 'upstream/master'

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

diff --git a/test/python/test_tokenizer_legacy.py b/test/python/test_tokenizer_legacy.py
index 3cd18fcff53f910210932f56ecd5ed7300d64c98..53d45c1c93a0f44f375ab11b675902497789b73e 100644 (file)
--- a/test/python/test_tokenizer_legacy.py
+++ b/test/python/test_tokenizer_legacy.py
@@ -5,6 +5,7 @@ import shutil
 
 import pytest
 
 
 import pytest
 

+from nominatim.indexer.place_info import PlaceInfo

 from nominatim.tokenizer import legacy_tokenizer
 from nominatim.db import properties
 from nominatim.errors import UsageError
 from nominatim.tokenizer import legacy_tokenizer
 from nominatim.db import properties
 from nominatim.errors import UsageError


@@ -73,7 +74,7 @@ def analyzer(tokenizer_factory, test_config, monkeypatch, sql_preprocessor,
 @pytest.fixture
 def make_standard_name(temp_db_cursor):
     temp_db_cursor.execute("""CREATE OR REPLACE FUNCTION make_standard_name(name TEXT)
 @pytest.fixture
 def make_standard_name(temp_db_cursor):
     temp_db_cursor.execute("""CREATE OR REPLACE FUNCTION make_standard_name(name TEXT)

-                              RETURNS TEXT AS $$ SELECT ' ' || name; $$ LANGUAGE SQL""")
+                              RETURNS TEXT AS $$ SELECT '#' || lower(name) || '#'; $$ LANGUAGE SQL""")

 
 
 @pytest.fixture
 
 
 @pytest.fixture


@@ -131,10 +132,10 @@ def test_init_module_custom(tokenizer_factory, test_config,
     assert not (test_config.project_dir / 'module').exists()
 
 
     assert not (test_config.project_dir / 'module').exists()
 
 

-def test_init_from_project(tokenizer_setup, tokenizer_factory):
+def test_init_from_project(tokenizer_setup, tokenizer_factory, test_config):

     tok = tokenizer_factory()
 
     tok = tokenizer_factory()
 

-    tok.init_from_project()
+    tok.init_from_project(test_config)

 
     assert tok.normalization is not None
 
 
     assert tok.normalization is not None
 


@@ -209,18 +210,19 @@ def test_update_special_phrase_empty_table(analyzer, word_table, make_standard_n
     analyzer.update_special_phrases([
         ("König bei", "amenity", "royal", "near"),
         ("Könige", "amenity", "royal", "-"),
     analyzer.update_special_phrases([
         ("König bei", "amenity", "royal", "near"),
         ("Könige", "amenity", "royal", "-"),

+        ("könige", "amenity", "royal", "-"),

         ("strasse", "highway", "primary", "in")
     ], True)
 
     assert word_table.get_special() \
         ("strasse", "highway", "primary", "in")
     ], True)
 
     assert word_table.get_special() \

-               == set(((' könig bei', 'könig bei', 'amenity', 'royal', 'near'),
-                       (' könige', 'könige', 'amenity', 'royal', None),
-                       (' strasse', 'strasse', 'highway', 'primary', 'in')))
+               == set(((' #könig bei#', 'könig bei', 'amenity', 'royal', 'near'),
+                       (' #könige#', 'könige', 'amenity', 'royal', None),
+                       (' #strasse#', 'strasse', 'highway', 'primary', 'in')))

 
 
 def test_update_special_phrase_delete_all(analyzer, word_table, make_standard_name):
 
 
 def test_update_special_phrase_delete_all(analyzer, word_table, make_standard_name):

-    word_table.add_special(' foo', 'foo', 'amenity', 'prison', 'in')
-    word_table.add_special(' bar', 'bar', 'highway', 'road', None)
+    word_table.add_special(' #foo#', 'foo', 'amenity', 'prison', 'in')
+    word_table.add_special(' #bar#', 'bar', 'highway', 'road', None)

 
     assert word_table.count_special() == 2
 
 
     assert word_table.count_special() == 2
 


@@ -230,8 +232,8 @@ def test_update_special_phrase_delete_all(analyzer, word_table, make_standard_na
 
 
 def test_update_special_phrases_no_replace(analyzer, word_table, make_standard_name):
 
 
 def test_update_special_phrases_no_replace(analyzer, word_table, make_standard_name):

-    word_table.add_special(' foo', 'foo', 'amenity', 'prison', 'in')
-    word_table.add_special(' bar', 'bar', 'highway', 'road', None)
+    word_table.add_special(' #foo#', 'foo', 'amenity', 'prison', 'in')
+    word_table.add_special(' #bar#', 'bar', 'highway', 'road', None)

 
     assert word_table.count_special() == 2
 
 
     assert word_table.count_special() == 2
 


@@ -241,8 +243,8 @@ def test_update_special_phrases_no_replace(analyzer, word_table, make_standard_n
 
 
 def test_update_special_phrase_modify(analyzer, word_table, make_standard_name):
 
 
 def test_update_special_phrase_modify(analyzer, word_table, make_standard_name):

-    word_table.add_special(' foo', 'foo', 'amenity', 'prison', 'in')
-    word_table.add_special(' bar', 'bar', 'highway', 'road', None)
+    word_table.add_special(' #foo#', 'foo', 'amenity', 'prison', 'in')
+    word_table.add_special(' #bar#', 'bar', 'highway', 'road', None)

 
     assert word_table.count_special() == 2
 
 
     assert word_table.count_special() == 2
 


@@ -253,27 +255,51 @@ def test_update_special_phrase_modify(analyzer, word_table, make_standard_name):
     ], True)
 
     assert word_table.get_special() \
     ], True)
 
     assert word_table.get_special() \

-               == set(((' prison', 'prison', 'amenity', 'prison', 'in'),
-                       (' bar', 'bar', 'highway', 'road', None),
-                       (' garden', 'garden', 'leisure', 'garden', 'near')))
+               == set(((' #prison#', 'prison', 'amenity', 'prison', 'in'),
+                       (' #bar#', 'bar', 'highway', 'road', None),
+                       (' #garden#', 'garden', 'leisure', 'garden', 'near')))
+
+
+def test_add_country_names(analyzer, word_table, make_standard_name):
+    analyzer.add_country_names('de', {'name': 'Germany',
+                                      'name:de': 'Deutschland',
+                                      'short_name': 'germany'})
+
+    assert word_table.get_country() \
+               == {('de', ' #germany#'),
+                   ('de', ' #deutschland#')}
+
+
+def test_add_more_country_names(analyzer, word_table, make_standard_name):
+    word_table.add_country('fr', ' #france#')
+    word_table.add_country('it', ' #italy#')
+    word_table.add_country('it', ' #itala#')
+
+    analyzer.add_country_names('it', {'name': 'Italy', 'ref': 'IT'})
+
+    assert word_table.get_country() \
+               == {('fr', ' #france#'),
+                   ('it', ' #italy#'),
+                   ('it', ' #itala#'),
+                   ('it', ' #it#')}

 
 
 def test_process_place_names(analyzer, make_keywords):
 
 
 def test_process_place_names(analyzer, make_keywords):

-    info = analyzer.process_place({'name' : {'name' : 'Soft bAr', 'ref': '34'}})
+    info = analyzer.process_place(PlaceInfo({'name' : {'name' : 'Soft bAr', 'ref': '34'}}))

 
     assert info['names'] == '{1,2,3}'
 
 
 @pytest.mark.parametrize('pcode', ['12345', 'AB 123', '34-345'])
 def test_process_place_postcode(analyzer, create_postcode_id, word_table, pcode):
 
     assert info['names'] == '{1,2,3}'
 
 
 @pytest.mark.parametrize('pcode', ['12345', 'AB 123', '34-345'])
 def test_process_place_postcode(analyzer, create_postcode_id, word_table, pcode):

-    analyzer.process_place({'address': {'postcode' : pcode}})
+    analyzer.process_place(PlaceInfo({'address': {'postcode' : pcode}}))

 
     assert word_table.get_postcodes() == {pcode, }
 
 
 @pytest.mark.parametrize('pcode', ['12:23', 'ab;cd;f', '123;836'])
 def test_process_place_bad_postcode(analyzer, create_postcode_id, word_table, pcode):
 
     assert word_table.get_postcodes() == {pcode, }
 
 
 @pytest.mark.parametrize('pcode', ['12:23', 'ab;cd;f', '123;836'])
 def test_process_place_bad_postcode(analyzer, create_postcode_id, word_table, pcode):

-    analyzer.process_place({'address': {'postcode' : pcode}})
+    analyzer.process_place(PlaceInfo({'address': {'postcode' : pcode}}))

 
     assert not word_table.get_postcodes()
 
 
     assert not word_table.get_postcodes()
 


@@ -294,7 +320,7 @@ class TestHousenumberName:
     @staticmethod
     @pytest.mark.parametrize('hnr', ['123a', '1', '101'])
     def test_process_place_housenumbers_simple(analyzer, hnr):
     @staticmethod
     @pytest.mark.parametrize('hnr', ['123a', '1', '101'])
     def test_process_place_housenumbers_simple(analyzer, hnr):

-        info = analyzer.process_place({'address': {'housenumber' : hnr}})
+        info = analyzer.process_place(PlaceInfo({'address': {'housenumber' : hnr}}))

 
         assert info['hnr'] == hnr
         assert info['hnr_tokens'].startswith("{")
 
         assert info['hnr'] == hnr
         assert info['hnr_tokens'].startswith("{")


@@ -302,15 +328,15 @@ class TestHousenumberName:
 
     @staticmethod
     def test_process_place_housenumbers_lists(analyzer):
 
     @staticmethod
     def test_process_place_housenumbers_lists(analyzer):

-        info = analyzer.process_place({'address': {'conscriptionnumber' : '1; 2;3'}})
+        info = analyzer.process_place(PlaceInfo({'address': {'conscriptionnumber' : '1; 2;3'}}))

 
         assert set(info['hnr'].split(';')) == set(('1', '2', '3'))
 
 
     @staticmethod
     def test_process_place_housenumbers_duplicates(analyzer):
 
         assert set(info['hnr'].split(';')) == set(('1', '2', '3'))
 
 
     @staticmethod
     def test_process_place_housenumbers_duplicates(analyzer):

-        info = analyzer.process_place({'address': {'housenumber' : '134',
+        info = analyzer.process_place(PlaceInfo({'address': {'housenumber' : '134',

                                                    'conscriptionnumber' : '134',
                                                    'conscriptionnumber' : '134',

-                                                   'streetnumber' : '99a'}})
+                                                   'streetnumber' : '99a'}}))

 
         assert set(info['hnr'].split(';')) == set(('134', '99a'))
 
         assert set(info['hnr'].split(';')) == set(('134', '99a'))