Harden external file connector boundaries

This commit is contained in:
2026-07-21 12:10:23 +02:00
parent 3bc1d3489e
commit f2dfb6c90e
18 changed files with 1167 additions and 64 deletions

View File

@@ -0,0 +1,239 @@
from __future__ import annotations
import socket
import ssl
import select
from collections.abc import Mapping
from contextlib import contextmanager
from dataclasses import dataclass
from typing import Any, Iterator
import httpcore
import httpx
from govoplan_core.security.outbound_http import (
OutboundHttpError,
bounded_chunks_bytes,
create_outbound_connection,
response_limit,
validate_outbound_http_url,
)
class ConnectorHttpError(RuntimeError):
pass
@dataclass(frozen=True, slots=True)
class ConnectorHttpResponse:
status_code: int
headers: Mapping[str, str]
content: bytes
_HTTPCORE_TRANSPORT_ERRORS = (
httpcore.TimeoutException,
httpcore.NetworkError,
httpcore.ProtocolError,
httpcore.ProxyError,
httpcore.UnsupportedProtocol,
)
class _SocketNetworkStream(httpcore.NetworkStream):
"""Public httpcore NetworkStream adapter around an approved socket."""
def __init__(self, sock: socket.socket) -> None:
self._socket = sock
def read(self, max_bytes: int, timeout: float | None = None) -> bytes:
try:
self._socket.settimeout(timeout)
return self._socket.recv(max_bytes)
except socket.timeout as exc:
raise httpcore.ReadTimeout(str(exc)) from exc
except OSError as exc:
raise httpcore.ReadError(str(exc)) from exc
def write(self, buffer: bytes, timeout: float | None = None) -> None:
try:
self._socket.settimeout(timeout)
self._socket.sendall(buffer)
except socket.timeout as exc:
raise httpcore.WriteTimeout(str(exc)) from exc
except OSError as exc:
raise httpcore.WriteError(str(exc)) from exc
def close(self) -> None:
self._socket.close()
def start_tls(
self,
ssl_context: ssl.SSLContext,
server_hostname: str | None = None,
timeout: float | None = None,
) -> httpcore.NetworkStream:
try:
self._socket.settimeout(timeout)
tls_socket = ssl_context.wrap_socket(self._socket, server_hostname=server_hostname)
except socket.timeout as exc:
self.close()
raise httpcore.ConnectTimeout(str(exc)) from exc
except OSError as exc:
self.close()
raise httpcore.ConnectError(str(exc)) from exc
return _SocketNetworkStream(tls_socket)
def get_extra_info(self, info: str) -> Any:
if info == "ssl_object" and isinstance(self._socket, ssl.SSLSocket):
return self._socket
if info == "client_addr":
return self._socket.getsockname()
if info == "server_addr":
return self._socket.getpeername()
if info == "socket":
return self._socket
if info == "is_readable":
try:
return bool(select.select([self._socket], [], [], 0)[0])
except (OSError, ValueError):
return True
return None
class _OutboundPolicyNetworkBackend(httpcore.NetworkBackend):
def connect_tcp(
self,
host: str,
port: int,
timeout: float | None = None,
local_address: str | None = None,
socket_options: Any = None,
) -> httpcore.NetworkStream:
source_address = None if local_address is None else (local_address, 0)
try:
sock = create_outbound_connection(
host,
port,
timeout=timeout,
source_address=source_address,
socket_options=socket_options,
label="File connector HTTP endpoint",
)
except socket.timeout as exc:
raise httpcore.ConnectTimeout(str(exc)) from exc
except (OSError, OutboundHttpError) as exc:
raise httpcore.ConnectError(str(exc)) from exc
return _SocketNetworkStream(sock)
def connect_unix_socket(self, path: str, timeout: float | None = None, socket_options: Any = None): # type: ignore[no-untyped-def]
del path, timeout, socket_options
raise httpcore.ConnectError("Unix sockets are not supported for file connectors")
class _HttpcoreResponseStream(httpx.SyncByteStream):
def __init__(self, stream: Any, *, request: httpx.Request) -> None:
self._stream = stream
self._request = request
def __iter__(self): # type: ignore[no-untyped-def]
try:
yield from self._stream
except _HTTPCORE_TRANSPORT_ERRORS as exc:
raise httpx.TransportError(str(exc), request=self._request) from exc
def close(self) -> None:
if hasattr(self._stream, "close"):
self._stream.close()
class _OutboundPolicyHTTPTransport(httpx.BaseTransport):
def __init__(self) -> None:
self._connection_pool = httpcore.ConnectionPool(
ssl_context=httpx.create_ssl_context(verify=True, trust_env=False),
max_connections=100,
max_keepalive_connections=20,
keepalive_expiry=5.0,
network_backend=_OutboundPolicyNetworkBackend(),
)
def handle_request(self, request: httpx.Request) -> httpx.Response:
core_request = httpcore.Request(
method=request.method,
url=httpcore.URL(
scheme=request.url.raw_scheme,
host=request.url.raw_host,
port=request.url.port,
target=request.url.raw_path,
),
headers=request.headers.raw,
content=request.stream,
extensions=request.extensions,
)
try:
response = self._connection_pool.handle_request(core_request)
except _HTTPCORE_TRANSPORT_ERRORS as exc:
raise httpx.TransportError(str(exc), request=request) from exc
return httpx.Response(
status_code=response.status,
headers=response.headers,
stream=_HttpcoreResponseStream(response.stream, request=request),
extensions=response.extensions,
)
def close(self) -> None:
self._connection_pool.close()
@contextmanager
def _stream_connector_request(method: str, url: str, **kwargs: Any) -> Iterator[httpx.Response]:
with httpx.Client(
transport=_OutboundPolicyHTTPTransport(),
follow_redirects=False,
timeout=kwargs.pop("timeout", 15.0),
) as client:
with client.stream(method, url, **kwargs) as response:
yield response
def request_connector_bytes(
method: str,
url: str,
*,
headers: Mapping[str, str] | None = None,
params: Mapping[str, str] | None = None,
data: Mapping[str, str] | bytes | str | None = None,
content: bytes | str | None = None,
auth: Any = None,
timeout: float = 15.0,
kind: str = "structured",
max_bytes: int | None = None,
label: str = "File connector",
) -> ConnectorHttpResponse:
try:
validated_url = validate_outbound_http_url(url, label=f"{label} URL")
effective_limit = response_limit(kind) if max_bytes is None else min(int(max_bytes), response_limit(kind))
with _stream_connector_request(
method,
validated_url,
headers=dict(headers or {}),
params=params,
data=data,
content=content,
auth=auth,
timeout=timeout,
) as response:
body = bounded_chunks_bytes(
response.iter_bytes(),
headers=response.headers,
max_bytes=effective_limit,
kind=kind,
label=f"{label} response",
)
return ConnectorHttpResponse(
status_code=response.status_code,
headers=dict(response.headers),
content=body,
)
except (httpx.HTTPError, OutboundHttpError, ValueError) as exc:
raise ConnectorHttpError(str(exc)) from exc