mirror of
https://github.com/osm-search/Nominatim.git
synced 2026-02-14 18:37:58 +00:00
0d423ad7a7
Now follows the same pattern as fixtures for other tables and uses the production SQL for table creation.
80 lines
3.1 KiB
Python
80 lines
3.1 KiB
Python
# SPDX-License-Identifier: GPL-2.0-only
|
|
#
|
|
# This file is part of Nominatim. (https://nominatim.org)
|
|
#
|
|
# Copyright (C) 2026 by the Nominatim developer community.
|
|
# For a full list of authors see the git log.
|
|
"""
|
|
Tests for correctly assigning wikipedia pages to places.
|
|
"""
|
|
import gzip
|
|
import csv
|
|
|
|
import pytest
|
|
|
|
from nominatim_db.tools.refresh import (import_wikipedia_articles,
|
|
recompute_importance,
|
|
create_functions)
|
|
|
|
|
|
@pytest.fixture
|
|
def wiki_csv(tmp_path, sql_preprocessor):
|
|
def _import(data):
|
|
with gzip.open(tmp_path / 'wikimedia-importance.csv.gz', mode='wt', encoding='utf-8') as fd:
|
|
writer = csv.DictWriter(fd, fieldnames=['language', 'type', 'title',
|
|
'importance', 'wikidata_id'],
|
|
delimiter='\t', quotechar='|')
|
|
writer.writeheader()
|
|
for lang, title, importance, wd in data:
|
|
writer.writerow({'language': lang, 'type': 'a',
|
|
'title': title, 'importance': str(importance),
|
|
'wikidata_id': wd})
|
|
return tmp_path
|
|
|
|
return _import
|
|
|
|
|
|
@pytest.mark.parametrize('extra', [{'wikipedia:en': 'Test'},
|
|
{'wikipedia': 'en:Test'},
|
|
{'wikidata': 'Q123'}])
|
|
def test_wikipedia(dsn, temp_db_conn, temp_db_cursor, table_factory,
|
|
def_config, wiki_csv, placex_row, extra):
|
|
import_wikipedia_articles(dsn, wiki_csv([('en', 'Test', 0.3, 'Q123')]))
|
|
create_functions(temp_db_conn, def_config)
|
|
|
|
content = temp_db_cursor.row_set(
|
|
'SELECT language, title, importance, wikidata FROM wikimedia_importance')
|
|
assert content == set([('en', 'Test', 0.3, 'Q123')])
|
|
|
|
place_id = placex_row(osm_id=12, extratags=extra)
|
|
table_factory('search_name',
|
|
'place_id BIGINT, importance FLOAT',
|
|
[(place_id, 0.2)])
|
|
|
|
recompute_importance(temp_db_conn)
|
|
|
|
content = temp_db_cursor.row_set('SELECT wikipedia, importance FROM placex')
|
|
assert content == set([('en:Test', 0.3)])
|
|
simp = temp_db_cursor.scalar('SELECT importance FROM search_name WHERE place_id = %s',
|
|
(place_id,))
|
|
assert simp == 0.3
|
|
|
|
|
|
def test_wikipedia_no_match(dsn, temp_db_conn, temp_db_cursor, def_config, wiki_csv,
|
|
placex_row, table_factory):
|
|
import_wikipedia_articles(dsn, wiki_csv([('de', 'Test', 0.3, 'Q123')]))
|
|
create_functions(temp_db_conn, def_config)
|
|
|
|
place_id = placex_row(osm_id=12, extratags={'wikipedia': 'en:Test'}, rank_search=10)
|
|
table_factory('search_name',
|
|
'place_id BIGINT, importance FLOAT',
|
|
[(place_id, 0.2)])
|
|
|
|
recompute_importance(temp_db_conn)
|
|
|
|
content = temp_db_cursor.row_set('SELECT wikipedia, importance FROM placex')
|
|
assert list(content) == [(None, pytest.approx(0.26667666))]
|
|
simp = temp_db_cursor.scalar('SELECT importance FROM search_name WHERE place_id = %s',
|
|
(place_id,))
|
|
assert simp == pytest.approx(0.26667666)
|