Files
frigate/frigate/db/sqlitevecq.py
T
Josh HawkinsandGitHub c2e739b4bc
CI / AMD64 Build (push) Waiting to run
CI / ARM Build (push) Waiting to run
CI / Jetson Jetpack 6 (push) Waiting to run
CI / ARM Extra Build (push) Blocked by required conditions
CI / Synaptics Build (push) Blocked by required conditions
CI / Assemble and push default build (push) Blocked by required conditions
CI / AMD64 Extra Build (push) Blocked by required conditions
bound REGEXP evaluation with a timeout to prevent ReDoS on the database thread (#23714)
The recognized_license_plate event filter passed attacker-controlled patterns to re.search on the single serialized SQLite queue thread, letting any authenticated user freeze the whole application with a catastrophic regex. This swaps stdlib re for the regex module with a per-evaluation timeout so a pathological pattern is aborted instead of stalling every database operation.
2026-07-14 06:27:00 -05:00

77 lines
2.7 KiB
Python

import sqlite3
from typing import Any
import regex
from playhouse.sqliteq import SqliteQueueDatabase
REGEXP_TIMEOUT_SECONDS = 1.0
class SqliteVecQueueDatabase(SqliteQueueDatabase):
def __init__(
self, *args: Any, load_vec_extension: bool = False, **kwargs: Any
) -> None:
self.load_vec_extension: bool = load_vec_extension
# no extension necessary, sqlite will load correctly for each platform
self.sqlite_vec_path = "/usr/local/lib/vec0"
super().__init__(*args, **kwargs)
def _connect(self, *args: Any, **kwargs: Any) -> sqlite3.Connection:
conn: sqlite3.Connection = super()._connect(*args, **kwargs) # type: ignore[misc]
if self.load_vec_extension:
self._load_vec_extension(conn)
# register REGEXP support
self._register_regexp(conn)
return conn
def _load_vec_extension(self, conn: sqlite3.Connection) -> None:
conn.enable_load_extension(True)
conn.load_extension(self.sqlite_vec_path)
conn.enable_load_extension(False)
def _register_regexp(self, conn: sqlite3.Connection) -> None:
def regexp(expr: str, item: str | None) -> bool:
if item is None:
return False
try:
return (
regex.search(expr, item, timeout=REGEXP_TIMEOUT_SECONDS) is not None
)
except (regex.error, TimeoutError):
return False
conn.create_function("REGEXP", 2, regexp)
def delete_embeddings_thumbnail(self, event_ids: list[str]) -> None:
ids = ",".join(["?" for _ in event_ids])
self.execute_sql(f"DELETE FROM vec_thumbnails WHERE id IN ({ids})", event_ids)
def delete_embeddings_description(self, event_ids: list[str]) -> None:
ids = ",".join(["?" for _ in event_ids])
self.execute_sql(f"DELETE FROM vec_descriptions WHERE id IN ({ids})", event_ids)
def drop_embeddings_tables(self) -> None:
self.execute_sql("""
DROP TABLE vec_descriptions;
""")
self.execute_sql("""
DROP TABLE vec_thumbnails;
""")
def create_embeddings_tables(self) -> None:
"""Create vec0 virtual table for embeddings"""
self.execute_sql("""
CREATE VIRTUAL TABLE IF NOT EXISTS vec_thumbnails USING vec0(
id TEXT PRIMARY KEY,
thumbnail_embedding FLOAT[768] distance_metric=cosine
);
""")
self.execute_sql("""
CREATE VIRTUAL TABLE IF NOT EXISTS vec_descriptions USING vec0(
id TEXT PRIMARY KEY,
description_embedding FLOAT[768] distance_metric=cosine
);
""")