84 lines
3.5 KiB
Python
84 lines
3.5 KiB
Python
"""Persistence and signed snapshots for search relevance reviews."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import base64
|
|
import hashlib
|
|
import hmac
|
|
import json
|
|
import secrets
|
|
import sqlite3
|
|
import threading
|
|
import time
|
|
from pathlib import Path
|
|
|
|
|
|
MAX_COMMENT = 4000
|
|
MAX_REVIEWER = 120
|
|
|
|
|
|
class ReviewStore:
|
|
def __init__(self, path: Path | str = ":memory:"):
|
|
if path != ":memory:":
|
|
Path(path).parent.mkdir(parents=True, exist_ok=True)
|
|
self.connection = sqlite3.connect(path, check_same_thread=False)
|
|
self.connection.row_factory = sqlite3.Row
|
|
# ponytail: one SQLite lock; split connections only if review throughput matters.
|
|
self._lock = threading.Lock()
|
|
self.connection.execute("""
|
|
CREATE TABLE IF NOT EXISTS search_reviews (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
created_at TEXT NOT NULL,
|
|
reviewer TEXT NOT NULL,
|
|
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
|
|
)
|
|
""")
|
|
self.connection.commit()
|
|
|
|
def save(self, review: dict) -> int:
|
|
with self._lock:
|
|
cursor = self.connection.execute(
|
|
"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)
|
|
|
|
def export(self) -> list[dict]:
|
|
with self._lock:
|
|
return [
|
|
{**dict(row), "results": json.loads(row["results_json"])}
|
|
for row in self.connection.execute("SELECT * FROM search_reviews ORDER BY id")
|
|
]
|
|
|
|
|
|
class ReviewSnapshots:
|
|
def __init__(self, secret: bytes | None = None, ttl: int = 3600):
|
|
self.secret = secret or secrets.token_bytes(32)
|
|
self.ttl = 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}"
|
|
|
|
def verify(self, token: str) -> dict:
|
|
try:
|
|
encoded, signature = token.split(".", 1)
|
|
expected = hmac.new(self.secret, encoded.encode(), hashlib.sha256).hexdigest()
|
|
if not hmac.compare_digest(signature, expected):
|
|
raise ValueError
|
|
payload = json.loads(base64.urlsafe_b64decode(encoded + "=" * (-len(encoded) % 4)))
|
|
if payload["expires_at"] < int(time.time()):
|
|
raise ValueError
|
|
return payload
|
|
except (ValueError, KeyError, TypeError, json.JSONDecodeError, UnicodeError) as error:
|
|
raise ValueError("invalid or expired search snapshot") from error
|