fix: make review snapshots reproducible
This commit is contained in:
@@ -150,7 +150,9 @@ class Api:
|
||||
raise ApiError(502, "search backend returned an incomplete response") from error
|
||||
results = [self.search_hit(hit, language) for hit in hits[:page_size]]
|
||||
snapshot_results = [{"rank": rank, **result} for rank, result in enumerate(results, 1)]
|
||||
return {"api_version": API_VERSION, "query": text, "language": language, "page": page, "page_size": page_size, "has_next": len(hits) > page_size, "results": results, "review_token": self.review_snapshots.create(text, language, self.index, snapshot_results)}
|
||||
concrete_indexes = {hit.get("_index") for hit in hits[:page_size] if hit.get("_index")}
|
||||
index_name = next(iter(concrete_indexes)) if len(concrete_indexes) == 1 else self.index
|
||||
return {"api_version": API_VERSION, "query": text, "language": language, "page": page, "page_size": page_size, "has_next": len(hits) > page_size, "results": results, "review_token": self.review_snapshots.create(text, language, index_name, snapshot_results, API_VERSION)}
|
||||
|
||||
@staticmethod
|
||||
def search_hit(hit: dict, language: str) -> dict:
|
||||
@@ -246,6 +248,8 @@ class Api:
|
||||
if not isinstance(submitted, list):
|
||||
raise ApiError(400, "results must be an array")
|
||||
by_rank = {item["rank"]: item for item in snapshot["results"]}
|
||||
if len(submitted) != len(by_rank) or {item.get("rank") for item in submitted if isinstance(item, dict)} != set(by_rank):
|
||||
raise ApiError(400, "all search results must be reviewed exactly once")
|
||||
results = []
|
||||
for item in submitted:
|
||||
if not isinstance(item, dict) or not isinstance(item.get("rank"), int) or item["rank"] not in by_rank:
|
||||
@@ -262,7 +266,7 @@ class Api:
|
||||
results.append({**source, "rating": rating, "comment": comment.strip()})
|
||||
if not results:
|
||||
raise ApiError(400, "at least one result must be reviewed")
|
||||
review = {"created_at": datetime.datetime.now(datetime.timezone.utc).isoformat(), "reviewer": reviewer, "query": snapshot["query"], "language": snapshot["language"], "index_name": snapshot["index_name"], "top_result_code": snapshot["results"][0]["code"] if snapshot["results"] else None, "results": results, "overall_comment": overall_comment}
|
||||
review = {"created_at": datetime.datetime.now(datetime.timezone.utc).isoformat(), "reviewer": reviewer, "query": snapshot["query"], "language": snapshot["language"], "index_name": snapshot["index_name"], "algorithm_version": snapshot["algorithm_version"], "top_result_code": snapshot["results"][0]["code"] if snapshot["results"] else None, "results": results, "overall_comment": overall_comment}
|
||||
review_id = self.review_store.save(review)
|
||||
return {"api_version": API_VERSION, "id": review_id, "created_at": review["created_at"]}
|
||||
|
||||
|
||||
@@ -33,6 +33,7 @@ class ReviewStore:
|
||||
query TEXT NOT NULL,
|
||||
language TEXT NOT NULL,
|
||||
index_name TEXT NOT NULL,
|
||||
algorithm_version TEXT NOT NULL,
|
||||
top_result_code TEXT,
|
||||
results_json TEXT NOT NULL,
|
||||
overall_comment TEXT NOT NULL
|
||||
@@ -43,8 +44,8 @@ class ReviewStore:
|
||||
def save(self, review: dict) -> int:
|
||||
with self._lock:
|
||||
cursor = self.connection.execute(
|
||||
"INSERT INTO search_reviews(created_at, reviewer, query, language, index_name, top_result_code, results_json, overall_comment) VALUES(?, ?, ?, ?, ?, ?, ?, ?)",
|
||||
(review["created_at"], review["reviewer"], review["query"], review["language"], review["index_name"], review["top_result_code"], json.dumps(review["results"], ensure_ascii=False), review["overall_comment"]),
|
||||
"INSERT INTO search_reviews(created_at, reviewer, query, language, index_name, algorithm_version, top_result_code, results_json, overall_comment) VALUES(?, ?, ?, ?, ?, ?, ?, ?, ?)",
|
||||
(review["created_at"], review["reviewer"], review["query"], review["language"], review["index_name"], review["algorithm_version"], review["top_result_code"], json.dumps(review["results"], ensure_ascii=False), review["overall_comment"]),
|
||||
)
|
||||
self.connection.commit()
|
||||
return int(cursor.lastrowid)
|
||||
@@ -62,8 +63,8 @@ class ReviewSnapshots:
|
||||
self.secret = secret or secrets.token_bytes(32)
|
||||
self.ttl = ttl
|
||||
|
||||
def create(self, query: str, language: str, index: str, results: list[dict]) -> str:
|
||||
payload = {"query": query, "language": language, "index_name": index, "results": results, "expires_at": int(time.time()) + self.ttl}
|
||||
def create(self, query: str, language: str, index: str, results: list[dict], algorithm_version: str) -> str:
|
||||
payload = {"query": query, "language": language, "index_name": index, "algorithm_version": algorithm_version, "results": results, "expires_at": int(time.time()) + self.ttl}
|
||||
encoded = base64.urlsafe_b64encode(json.dumps(payload, ensure_ascii=False, separators=(",", ":")).encode()).decode().rstrip("=")
|
||||
signature = hmac.new(self.secret, encoded.encode(), hashlib.sha256).hexdigest()
|
||||
return f"{encoded}.{signature}"
|
||||
|
||||
@@ -7,6 +7,15 @@ from search.api import Api, ApiError
|
||||
|
||||
|
||||
class SearchReviewTest(unittest.TestCase):
|
||||
def test_review_must_cover_each_snapshot_rank_once(self):
|
||||
with tempfile.TemporaryDirectory() as temporary:
|
||||
api = Api("http://opensearch:9200", "current", Path(temporary), Path(temporary) / "reviews.sqlite3", b"test-secret")
|
||||
response = {"hits": {"hits": [{"_index": "search-20260827", "_source": {"document_code": "7", "edition_code": "10", "document_name_ru": "Закон"}}, {"_index": "search-20260827", "_source": {"document_code": "8", "edition_code": "11", "document_name_ru": "Кодекс"}}]}}
|
||||
with patch("search.api.request_json", return_value=response):
|
||||
result = api.handle("GET", "/search?q=test&language=ru&page_size=2")[1]
|
||||
with self.assertRaisesRegex(ApiError, "exactly once"):
|
||||
api.handle("POST", "/search-reviews", {"review_token": result["review_token"], "reviewer": "Юрист", "results": [{"rank": 1, "code": "7", "rating": 3}]})
|
||||
|
||||
def test_saves_signed_search_snapshot_and_rejects_tampering(self):
|
||||
with tempfile.TemporaryDirectory() as temporary:
|
||||
api = Api("http://opensearch:9200", "current", Path(temporary), Path(temporary) / "reviews.sqlite3", b"test-secret")
|
||||
|
||||
Reference in New Issue
Block a user