reorganize and complete tests around generic token analysis

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

diff --git a/test/python/test_tools_postcodes.py b/test/python/test_tools_postcodes.py
index e0a62ec7572ff4b53d6254ff13be266dba0754f1..a34157690c8bd9350fe1881b442abdc970c4fdde 100644 (file)
--- a/test/python/test_tools_postcodes.py
+++ b/test/python/test_tools_postcodes.py
@@ -26,6 +26,11 @@ class MockPostcodeTable:
                                geometry GEOMETRY(Geometry, 4326))""")
             cur.execute("""CREATE OR REPLACE FUNCTION token_normalized_postcode(postcode TEXT)
                            RETURNS TEXT AS $$ BEGIN RETURN postcode; END; $$ LANGUAGE plpgsql;
+
+                           CREATE OR REPLACE FUNCTION get_country_code(place geometry)
+                           RETURNS TEXT AS $$ BEGIN 
+                           RETURN null;
+                           END; $$ LANGUAGE plpgsql;
                         """)
         conn.commit()
 
@@ -58,15 +63,16 @@ def postcode_table(temp_db_conn, placex_table, word_table):
     return MockPostcodeTable(temp_db_conn)
 
 
-def test_import_postcodes_empty(dsn, postcode_table, tmp_path, tokenizer):
+def test_postcodes_empty(dsn, postcode_table, place_table,
+                         tmp_path, tokenizer):
     postcodes.update_postcodes(dsn, tmp_path, tokenizer)
 
     assert not postcode_table.row_set
 
 
-def test_import_postcodes_add_new(dsn, placex_table, postcode_table, tmp_path, tokenizer):
-    placex_table.add(country='xx', geom='POINT(10 12)',
-                     address=dict(postcode='9486'))
+def test_postcodes_add_new(dsn, postcode_table, tmp_path,
+                           insert_implicit_postcode, tokenizer):
+    insert_implicit_postcode(1, 'xx', 'POINT(10 12)', dict(postcode='9486'))
     postcode_table.add('yy', '9486', 99, 34)
 
     postcodes.update_postcodes(dsn, tmp_path, tokenizer)
@@ -74,9 +80,9 @@ def test_import_postcodes_add_new(dsn, placex_table, postcode_table, tmp_path, t
     assert postcode_table.row_set == {('xx', '9486', 10, 12), }
 
 
-def test_import_postcodes_replace_coordinates(dsn, placex_table, postcode_table, tmp_path, tokenizer):
-    placex_table.add(country='xx', geom='POINT(10 12)',
-                     address=dict(postcode='AB 4511'))
+def test_postcodes_replace_coordinates(dsn, postcode_table, tmp_path,
+                                       insert_implicit_postcode, tokenizer):
+    insert_implicit_postcode(1, 'xx', 'POINT(10 12)', dict(postcode='AB 4511'))
     postcode_table.add('xx', 'AB 4511', 99, 34)
 
     postcodes.update_postcodes(dsn, tmp_path, tokenizer)
@@ -84,9 +90,9 @@ def test_import_postcodes_replace_coordinates(dsn, placex_table, postcode_table,
     assert postcode_table.row_set == {('xx', 'AB 4511', 10, 12)}
 
 
-def test_import_postcodes_replace_coordinates_close(dsn, placex_table, postcode_table, tmp_path, tokenizer):
-    placex_table.add(country='xx', geom='POINT(10 12)',
-                     address=dict(postcode='AB 4511'))
+def test_postcodes_replace_coordinates_close(dsn, postcode_table, tmp_path,
+                                             insert_implicit_postcode, tokenizer):
+    insert_implicit_postcode(1, 'xx', 'POINT(10 12)', dict(postcode='AB 4511'))
     postcode_table.add('xx', 'AB 4511', 10, 11.99999)
 
     postcodes.update_postcodes(dsn, tmp_path, tokenizer)
@@ -94,9 +100,9 @@ def test_import_postcodes_replace_coordinates_close(dsn, placex_table, postcode_
     assert postcode_table.row_set == {('xx', 'AB 4511', 10, 11.99999)}
 
 
-def test_import_postcodes_remove(dsn, placex_table, postcode_table, tmp_path, tokenizer):
-    placex_table.add(country='xx', geom='POINT(10 12)',
-                     address=dict(postcode='AB 4511'))
+def test_postcodes_remove(dsn, postcode_table, tmp_path,
+                          insert_implicit_postcode, tokenizer):
+    insert_implicit_postcode(1, 'xx', 'POINT(10 12)', dict(postcode='AB 4511'))
     postcode_table.add('xx', 'badname', 10, 12)
 
     postcodes.update_postcodes(dsn, tmp_path, tokenizer)
@@ -104,32 +110,27 @@ def test_import_postcodes_remove(dsn, placex_table, postcode_table, tmp_path, to
     assert postcode_table.row_set == {('xx', 'AB 4511', 10, 12)}
 
 
-def test_import_postcodes_ignore_empty_country(dsn, placex_table, postcode_table, tmp_path, tokenizer):
-    placex_table.add(country=None, geom='POINT(10 12)',
-                     address=dict(postcode='AB 4511'))
-
+def test_postcodes_ignore_empty_country(dsn, postcode_table, tmp_path,
+                                        insert_implicit_postcode, tokenizer):
+    insert_implicit_postcode(1, None, 'POINT(10 12)', dict(postcode='AB 4511'))
     postcodes.update_postcodes(dsn, tmp_path, tokenizer)
-
     assert not postcode_table.row_set
 
 
-def test_import_postcodes_remove_all(dsn, placex_table, postcode_table, tmp_path, tokenizer):
+def test_postcodes_remove_all(dsn, postcode_table, place_table,
+                              tmp_path, tokenizer):
     postcode_table.add('ch', '5613', 10, 12)
-
     postcodes.update_postcodes(dsn, tmp_path, tokenizer)
 
     assert not postcode_table.row_set
 
 
-def test_import_postcodes_multi_country(dsn, placex_table, postcode_table, tmp_path, tokenizer):
-    placex_table.add(country='de', geom='POINT(10 12)',
-                     address=dict(postcode='54451'))
-    placex_table.add(country='cc', geom='POINT(100 56)',
-                     address=dict(postcode='DD23 T'))
-    placex_table.add(country='de', geom='POINT(10.3 11.0)',
-                     address=dict(postcode='54452'))
-    placex_table.add(country='cc', geom='POINT(10.3 11.0)',
-                     address=dict(postcode='54452'))
+def test_postcodes_multi_country(dsn, postcode_table, tmp_path,
+                                 insert_implicit_postcode, tokenizer):
+    insert_implicit_postcode(1, 'de', 'POINT(10 12)', dict(postcode='54451'))
+    insert_implicit_postcode(2, 'cc', 'POINT(100 56)', dict(postcode='DD23 T'))
+    insert_implicit_postcode(3, 'de', 'POINT(10.3 11.0)', dict(postcode='54452'))
+    insert_implicit_postcode(4, 'cc', 'POINT(10.3 11.0)', dict(postcode='54452'))
 
     postcodes.update_postcodes(dsn, tmp_path, tokenizer)
 
@@ -140,10 +141,9 @@ def test_import_postcodes_multi_country(dsn, placex_table, postcode_table, tmp_p
 
 
 @pytest.mark.parametrize("gzipped", [True, False])
-def test_import_postcodes_extern(dsn, placex_table, postcode_table, tmp_path,
-                                 tokenizer, gzipped):
-    placex_table.add(country='xx', geom='POINT(10 12)',
-                     address=dict(postcode='AB 4511'))
+def test_postcodes_extern(dsn, postcode_table, tmp_path,
+                          insert_implicit_postcode, tokenizer, gzipped):
+    insert_implicit_postcode(1, 'xx', 'POINT(10 12)', dict(postcode='AB 4511'))
 
     extfile = tmp_path / 'xx_postcodes.csv'
     extfile.write_text("postcode,lat,lon\nAB 4511,-4,-1\nCD 4511,-5, -10")
@@ -157,3 +157,57 @@ def test_import_postcodes_extern(dsn, placex_table, postcode_table, tmp_path,
     assert postcode_table.row_set == {('xx', 'AB 4511', 10, 12),
                                       ('xx', 'CD 4511', -10, -5)}
 
+
+def test_postcodes_extern_bad_column(dsn, postcode_table, tmp_path, 
+                                     insert_implicit_postcode, tokenizer):
+    insert_implicit_postcode(1, 'xx', 'POINT(10 12)', dict(postcode='AB 4511'))
+
+    extfile = tmp_path / 'xx_postcodes.csv'
+    extfile.write_text("postode,lat,lon\nAB 4511,-4,-1\nCD 4511,-5, -10")
+
+    postcodes.update_postcodes(dsn, tmp_path, tokenizer)
+
+    assert postcode_table.row_set == {('xx', 'AB 4511', 10, 12)}
+
+
+def test_postcodes_extern_bad_number(dsn, insert_implicit_postcode,
+                                     postcode_table, tmp_path, tokenizer):
+    insert_implicit_postcode(1, 'xx', 'POINT(10 12)', dict(postcode='AB 4511'))
+
+    extfile = tmp_path / 'xx_postcodes.csv'
+    extfile.write_text("postcode,lat,lon\nXX 4511,-4,NaN\nCD 4511,-5, -10\n34,200,0")
+
+    postcodes.update_postcodes(dsn, tmp_path, tokenizer)
+
+    assert postcode_table.row_set == {('xx', 'AB 4511', 10, 12),
+                                      ('xx', 'CD 4511', -10, -5)}
+
+def test_can_compute(dsn, table_factory):
+    assert not postcodes.can_compute(dsn)
+    table_factory('place')
+    assert postcodes.can_compute(dsn)
+
+def test_no_placex_entry(dsn, tmp_path, temp_db_cursor, place_row, postcode_table, tokenizer):
+    #Rewrite the get_country_code function to verify its execution.
+    temp_db_cursor.execute("""
+        CREATE OR REPLACE FUNCTION get_country_code(place geometry)
+        RETURNS TEXT AS $$ BEGIN 
+        RETURN 'fr';
+        END; $$ LANGUAGE plpgsql;
+    """)
+    place_row(geom='SRID=4326;POINT(10 12)', address=dict(postcode='AB 4511'))
+    postcodes.update_postcodes(dsn, tmp_path, tokenizer)
+
+    assert postcode_table.row_set == {('fr', 'AB 4511', 10, 12)}
+
+@pytest.fixture
+def insert_implicit_postcode(placex_table, place_row):
+    """
+        Inserts data into the placex and place table
+        which can then be used to compute one postcode.
+    """
+    def _insert_implicit_postcode(osm_id, country, geometry, address):
+        placex_table.add(osm_id=osm_id, country=country, geom=geometry)
+        place_row(osm_id=osm_id, geom='SRID=4326;'+geometry, address=address)
+
+    return _insert_implicit_postcode