fix: expose curated search query

This commit is contained in:
2026-08-20 15:08:42 +03:00
parent dc5399de0a
commit e3f08426d5
4 changed files with 117 additions and 72 deletions

View File

@@ -4,7 +4,8 @@ import unittest
from pathlib import Path
from unittest.mock import patch
from search.evaluate_relevance import evaluate, load_queries, search_body
from search.evaluate_relevance import evaluate, load_queries
from search.query import build_search_body
class SearchRelevanceTest(unittest.TestCase):
@@ -28,16 +29,12 @@ class SearchRelevanceTest(unittest.TestCase):
path.write_text(json.dumps(queries, ensure_ascii=False), encoding="utf-8")
loaded = load_queries(path)
responses = [
{"hits": {"hits": [{"_source": {"document_code": code}} for code in ["7", "10", "8"]]}},
{"hits": {"hits": [{"_source": {"document_code": code}} for code in ["10", "9"]]}},
]
with patch("search.evaluate_relevance.request_json", side_effect=responses) as request:
with patch("search.evaluate_relevance.search_documents", side_effect=[["7", "10", "8"], ["10", "9"]]):
result = evaluate(loaded, "http://127.0.0.1:9200", "test", 10)
self.assertEqual(result["summary"], {"query_count": 2, "recall_at_10": 1.0, "mrr_at_10": 0.75})
self.assertEqual(result["queries"][0]["reciprocal_rank_at_10"], 1.0)
body = json.loads(request.call_args_list[0].args[2])
body = json.loads(build_search_body("ru", "трудовой договор", 10))
self.assertFalse(body["track_total_hits"])
self.assertEqual(body["collapse"], {"field": "document_code"})
self.assertEqual(body["query"]["bool"]["must"]["multi_match"]["type"], "cross_fields")
@@ -47,7 +44,7 @@ class SearchRelevanceTest(unittest.TestCase):
("ru", "как открыть ОсОО", "Действует"),
("ky", "ЖЧК ачуу тартиби", "Күчүндө"),
):
body = json.loads(search_body(language, query, 10))
body = json.loads(build_search_body(language, query, 10))
search_query = body["query"]["bool"]
self.assertEqual(search_query["minimum_should_match"], 1)
boosts = [clause["constant_score"] for clause in search_query["should"][1:]]
@@ -58,6 +55,15 @@ class SearchRelevanceTest(unittest.TestCase):
)
self.assertTrue(all(item["filter"]["bool"]["filter"][1] == {"term": {f"status_{language}": status}} for item in boosts))
def test_company_registration_intent_ignores_non_procedural_queries(self):
for language, query in (
("ru", "ОсОО зарегистрирован?"),
("ru", "кто зарегистрировал ОсОО"),
("ky", "ЖЧК ачык маалымат"),
):
body = json.loads(build_search_body(language, query, 10))
self.assertNotIn("should", body["query"]["bool"])
if __name__ == "__main__":
unittest.main()