Files
mcp-server/tests/unit/test_connection_tools.py
T
ClaudeandClaude Fable 5 6d7387b022 feat: simplify fetch_url allowlist + add update_connection tool
Part 1 — fetch_url validation simplification
  Now that Connection.allowed_url_hosts exists, it's the ONLY check.
  The old 2-label suffix-overlap rule against yarn_rm_url is gone.

  - Connection.allowed_url_hosts: list[str] = Field(default_factory=list)
    (was list[str] | None = None). Default empty list means the
    connection has no fetch access; the user must explicitly opt in
    via save_connection or update_connection.
  - _validate_url_host drops the yarn_rm_url parameter and the
    _host_suffix_overlap helper. Now: scheme/host/IP checks, then
    empty-reject, then glob match. Reject everything else.
  - fetch_url's error message now points the user at
    Connection.allowed_url_hosts as the fix.
  - The label-by-label glob check from the previous commit is kept
    (SSRF guard: 'ccam*' matches 'ccam50' but NOT 'ccam50.evil.com').

Part 2 — update_connection tool
  PATCH-style update for an existing Connection record. Only the
  fields the caller provides are changed. Same pattern as
  update_pending_job: req.model_dump(exclude_none=True), with
  'name' popped before passing to the store.

  To CLEAR a field (e.g. drop auth_password), use delete_connection
  + save_connection. This is YAGNI; the alternative (model_fields_set
  to distinguish 'omitted' from 'null') adds surface for bugs.

  - ConnectionStore.update(name, **fields): get, model_copy(update=...),
    save. Lock + atomic write. Re-validates the patched record.
  - update_connection tool function: passes fields through to the
    store, logs which fields were changed.
  - UpdateConnectionRequest Pydantic model: 12 mutable fields + name.
  - /update_connection route with operation_id='update_connection'.
  - 9 new unit tests in test_connection_tools.py (PATCH, dict/list
    replace-not-merge, unknown name 404, validation of patched record,
    disk persistence).
  - test_fetch_url.py: existing 21 tests updated; 3 new tests for
    the empty/None/missing allowed_url_hosts cases.
  - test_mcp_routes.py: assert 22 tool routes.
  - README: update_connection row added; fetch_url row updated.

Tests: 386 passed (up from 377, +9 net).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-09 11:46:07 +08:00

189 lines
6.5 KiB
Python

# coding=utf-8
import json
from pathlib import Path
import pytest
from spark_executor.core import connection_store
from spark_executor.tools import connections
@pytest.fixture(autouse=True)
def _fresh_store(tmp_path: Path, monkeypatch):
monkeypatch.setattr(connection_store, "DEFAULT_DATA_DIR", str(tmp_path))
monkeypatch.setattr(connection_store, "store", connection_store.ConnectionStore())
monkeypatch.setattr(connections, "store", connection_store.store)
return connection_store.store
# --- save_connection ---
def test_save_connection(_fresh_store):
out = connections.save_connection(name="prod", master="yarn")
assert out == {"name": "prod", "status": "SAVED"}
assert _fresh_store.get("prod") is not None
def test_save_connection_upserts(_fresh_store):
connections.save_connection(name="prod", master="yarn")
connections.save_connection(name="prod", master="spark://new:7077", deploy_mode="client")
assert _fresh_store.get("prod").master == "spark://new:7077"
assert _fresh_store.get("prod").deploy_mode == "client"
def test_save_connection_with_spark_conf(_fresh_store):
connections.save_connection(
name="dev",
master="yarn",
spark_conf={"spark.sql.shuffle.partitions": "200"},
)
assert _fresh_store.get("dev").spark_conf["spark.sql.shuffle.partitions"] == "200"
# --- list_connections ---
def test_list_connections_empty(_fresh_store):
assert connections.list_connections() == []
def test_list_connections_returns_all_saved(_fresh_store):
connections.save_connection(name="a", master="yarn")
connections.save_connection(name="b", master="spark://m:7077", deploy_mode="client")
out = connections.list_connections()
names = {c["name"] for c in out}
assert names == {"a", "b"}
masters = {c["name"]: c["master"] for c in out}
assert masters == {"a": "yarn", "b": "spark://m:7077"}
# --- get_connection ---
def test_get_connection_returns_dict(_fresh_store):
connections.save_connection(name="prod", master="yarn", deploy_mode="cluster")
out = connections.get_connection("prod")
assert out["name"] == "prod"
assert out["master"] == "yarn"
assert out["deploy_mode"] == "cluster"
assert out["yarn_rm_url"] is None
assert out["spark_conf"] == {}
assert out["ssl_verify"] is None
assert out["ssl_ca_bundle"] is None
def test_save_connection_preserves_ssl_fields(_fresh_store):
connections.save_connection(
name="secure",
master="yarn",
ssl_verify=False,
ssl_ca_bundle="/tmp/ca.crt",
)
out = connections.get_connection("secure")
assert out["ssl_verify"] is False
assert out["ssl_ca_bundle"] == "/tmp/ca.crt"
def test_save_connection_with_basic_auth(_fresh_store):
connections.save_connection(
name="secure",
master="yarn",
auth_type="basic",
auth_user="hdfs",
auth_password="secret",
)
out = connections.get_connection("secure")
assert out["auth_type"] == "basic"
assert out["auth_user"] == "hdfs"
assert out["auth_password"] == "secret"
def test_save_connection_invalid_auth_type_raises(_fresh_store):
with pytest.raises(ValueError, match="auth_type must be one of none/simple/basic/kerberos"):
connections.save_connection(
name="bad",
master="yarn",
auth_type="oauth",
)
def test_get_connection_unknown_raises(_fresh_store):
with pytest.raises(KeyError):
connections.get_connection("missing")
# --- delete_connection ---
def test_delete_connection_returns_status(_fresh_store):
connections.save_connection(name="prod", master="yarn")
assert connections.delete_connection("prod") == {"name": "prod", "status": "DELETED"}
assert _fresh_store.get("prod") is None
def test_delete_connection_unknown_raises(_fresh_store):
with pytest.raises(KeyError):
connections.delete_connection("missing")
def test_update_connection_changes_specified_field(_fresh_store):
connections.save_connection(name="prod", master="yarn")
out = connections.update_connection(name="prod", master="spark://new:7077")
assert out["master"] == "spark://new:7077"
assert _fresh_store.get("prod").master == "spark://new:7077"
def test_update_connection_keeps_omitted_fields(_fresh_store):
connections.save_connection(
name="prod",
master="yarn",
deploy_mode="client",
yarn_rm_url="http://rm:8088",
)
out = connections.update_connection(name="prod", deploy_mode="cluster")
assert out["deploy_mode"] == "cluster"
assert out["master"] == "yarn"
assert out["yarn_rm_url"] == "http://rm:8088"
def test_update_connection_with_no_fields_is_noop(_fresh_store):
connections.save_connection(name="prod", master="yarn", deploy_mode="client")
out = connections.update_connection(name="prod")
assert out["master"] == "yarn"
assert out["deploy_mode"] == "client"
def test_update_connection_allows_url_hosts_change(_fresh_store):
connections.save_connection(name="prod", master="yarn")
out = connections.update_connection(name="prod", allowed_url_hosts=["ccam*"])
assert out["allowed_url_hosts"] == ["ccam*"]
def test_update_connection_replaces_not_merges_dict(_fresh_store):
connections.save_connection(name="prod", master="yarn", spark_conf={"a": "1"})
out = connections.update_connection(name="prod", spark_conf={"b": "2"})
assert out["spark_conf"] == {"b": "2"}
def test_update_connection_replaces_not_merges_list(_fresh_store):
connections.save_connection(
name="prod",
master="yarn",
allowed_url_hosts=["ccam*"],
)
out = connections.update_connection(name="prod", allowed_url_hosts=["nm*"])
assert out["allowed_url_hosts"] == ["nm*"]
def test_update_connection_raises_for_unknown_name(_fresh_store):
with pytest.raises(KeyError, match="Connection not found"):
connections.update_connection(name="missing", master="yarn")
def test_update_connection_validates_patched_connection(_fresh_store):
connections.save_connection(name="prod", master="yarn")
with pytest.raises(ValueError, match="master must be"):
connections.update_connection(name="prod", master="http://bad")
def test_update_connection_persists_to_disk(_fresh_store, tmp_path):
connections.save_connection(name="prod", master="yarn")
connections.update_connection(name="prod", master="spark://new:7077")
raw = json.loads((tmp_path / "connections.json").read_text())
assert raw["prod"]["master"] == "spark://new:7077"