Files
govoplan-search/tests/test_dsar_provider.py
T

483 lines
17 KiB
Python

from __future__ import annotations
import json
import unittest
from datetime import UTC, datetime, timedelta
from sqlalchemy import create_engine
from sqlalchemy.orm import Session
from govoplan_core.core.dsar import (
DsarErasureActionRef,
DsarProvider,
DsarRecordRef,
DsarSubjectRef,
)
from govoplan_core.db.base import Base
from govoplan_core.privacy.dsar_workflow import (
create_data_subject_request,
search_data_subject_request,
)
from govoplan_search.backend.db.models import (
SearchIndexAclToken,
SearchIndexChangeQueue,
SearchIndexDocument,
)
from govoplan_search.backend.dsar_provider import (
SEARCH_DSAR_CAPABILITY,
SearchDsarProvider,
)
from govoplan_search.backend.manifest import manifest
NOW = datetime(2026, 8, 21, 17, 0, tzinfo=UTC)
class _Registry:
def __init__(self, provider: SearchDsarProvider, *, active: bool = True) -> None:
self.provider = provider
self.active = active
def capability_names(self):
return (SEARCH_DSAR_CAPABILITY,)
def capability_owner(self, name):
self._assert_capability(name)
return "search"
def tenant_entitlement_resolver(self):
active = self.active
class _Resolver:
@staticmethod
def resolve(session, tenant_id):
del session, tenant_id
return type(
"State",
(),
{"effective_modules": ("search",) if active else ()},
)()
return _Resolver()
def require_tenant_capability(self, name, session, **kwargs):
del session, kwargs
self._assert_capability(name)
return self.provider
def manifests(self):
return (type("Manifest", (), {"id": "search"})(),)
@staticmethod
def _assert_capability(name: str) -> None:
if name != SEARCH_DSAR_CAPABILITY:
raise KeyError(name)
class SearchDsarProviderTests(unittest.TestCase):
def setUp(self) -> None:
self.engine = create_engine("sqlite+pysqlite:///:memory:")
Base.metadata.create_all(self.engine)
self.session = Session(self.engine)
self.provider = SearchDsarProvider()
self.assertIsInstance(self.provider, DsarProvider)
self._seed()
self.session.commit()
def tearDown(self) -> None:
self.session.close()
self.engine.dispose()
def _document(
self,
*,
row_id: str,
tenant_id: str,
resource_id: str,
) -> SearchIndexDocument:
return SearchIndexDocument(
id=row_id,
tenant_id=tenant_id,
module_id="cases",
provider_id="cases.search",
resource_type="case",
resource_id=resource_id,
title="private-title-do-not-export",
summary="private-summary-do-not-export",
body="private-body-do-not-export",
keywords=["private-keyword-do-not-export"],
search_text="private-search-text-do-not-export",
url="/private-url-do-not-export",
visibility="restricted",
external_reference={"secret": "private-reference-do-not-export"},
metadata_={"secret": "private-metadata-do-not-export"},
content_hash="a" * 64,
source_revision="revision-1",
change_cursor="private-cursor-do-not-export",
source_updated_at=NOW,
language="simple",
index_version=1,
requires_authorization_recheck=True,
rebuild_id="private-rebuild-id-do-not-export",
active=True,
indexed_at=NOW,
)
def _seed(self) -> None:
document = self._document(
row_id="document-1",
tenant_id="tenant-1",
resource_id="case-1",
)
document.acl_tokens.extend(
(
SearchIndexAclToken(
id="acl-1",
token="account:account-1",
),
SearchIndexAclToken(
id="acl-2",
token="identity:identity-1",
),
)
)
unrelated = self._document(
row_id="document-2",
tenant_id="tenant-1",
resource_id="case-2",
)
unrelated.acl_tokens.append(
SearchIndexAclToken(
id="acl-3",
token="account:account-1",
)
)
other_tenant = self._document(
row_id="document-3",
tenant_id="tenant-2",
resource_id="case-1",
)
other_tenant.acl_tokens.append(
SearchIndexAclToken(
id="acl-4",
token="account:account-1",
)
)
self.session.add_all((document, unrelated, other_tenant))
self.session.add_all(
(
SearchIndexChangeQueue(
id="change-1",
change_id="change-public-1",
tenant_id="tenant-1",
provider_id="cases.search",
module_id="cases",
resource_type="case",
resource_id="case-1",
kind="upsert",
source_revision="revision-1",
source_cursor="private-source-cursor-do-not-export",
document_={"secret": "private-queue-document-do-not-export"},
occurred_at=NOW,
status="queued",
attempts=1,
available_at=NOW,
error="private-error-do-not-export",
),
SearchIndexChangeQueue(
id="change-2",
change_id="change-public-2",
tenant_id="tenant-1",
provider_id="cases.search",
module_id="cases",
resource_type="case",
resource_id="case-2",
kind="upsert",
source_revision="revision-1",
source_cursor="unrelated-private-cursor",
document_={"secret": "unrelated-private-document"},
occurred_at=NOW + timedelta(minutes=1),
status="queued",
attempts=0,
available_at=NOW,
),
)
)
def test_source_reference_exports_only_minimized_derived_rows(self) -> None:
records = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=DsarSubjectRef(external_references={"cases.case": "case-1"}),
)
self.assertEqual(
{"search_index_document", "search_index_change"},
{record.resource_type for record in records},
)
exported = json.dumps([record.to_dict() for record in records])
self.assertIn("case-1", exported)
self.assertNotIn("case-2", exported)
for secret in (
"private-title-do-not-export",
"private-summary-do-not-export",
"private-body-do-not-export",
"private-keyword-do-not-export",
"private-search-text-do-not-export",
"private-url-do-not-export",
"private-reference-do-not-export",
"private-metadata-do-not-export",
"private-cursor-do-not-export",
"private-rebuild-id-do-not-export",
"private-source-cursor-do-not-export",
"private-queue-document-do-not-export",
"private-error-do-not-export",
):
self.assertNotIn(secret, exported)
def test_canonical_selectors_export_acl_projection_not_source_content(self) -> None:
records = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=DsarSubjectRef(
account_id="account-1",
identity_id="identity-1",
),
)
self.assertEqual(
{"search_acl_projection"},
{record.resource_type for record in records},
)
self.assertEqual(3, len(records))
exported = json.dumps([record.to_dict() for record in records])
self.assertNotIn("account-1", exported)
self.assertNotIn("identity-1", exported)
self.assertNotIn("private-title-do-not-export", exported)
self.assertNotIn("document-3", exported)
def test_direct_references_and_conflicts_fail_closed(self) -> None:
direct = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=DsarSubjectRef(
external_references={"search.document": "document-1"}
),
)
conflict = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=DsarSubjectRef(
external_references={
"search.document": "document-1",
"cases.case": "case-2",
}
),
)
alias_conflict = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=DsarSubjectRef(
external_references={
"search.document": "document-1",
"search.index_document": "document-2",
}
),
)
wrong_tenant = self.provider.search_subject(
self.session,
tenant_id="tenant-2",
subject=DsarSubjectRef(
external_references={"search.document": "document-1"}
),
)
wrong_resource_type = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=DsarSubjectRef(external_references={"cases.ticket": "case-1"}),
)
change_and_account = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=DsarSubjectRef(
account_id="account-1",
external_references={"search.change": "change-1"},
),
)
self.assertEqual(["document-1"], [record.resource_id for record in direct])
self.assertEqual((), conflict)
self.assertEqual((), alias_conflict)
self.assertEqual((), wrong_tenant)
self.assertEqual((), wrong_resource_type)
self.assertEqual(
{"change-1", "acl-1"},
{record.resource_id for record in change_and_account},
)
def test_derived_deletion_is_idempotent_but_acl_review_is_blocked(self) -> None:
direct_subject = DsarSubjectRef(external_references={"cases.case": "case-1"})
direct_records = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=direct_subject,
)
actions = self.provider.plan_erasure(
self.session,
tenant_id="tenant-1",
subject=direct_subject,
records=direct_records,
)
self.assertTrue(actions)
self.assertTrue(all(action.kind == "delete" for action in actions))
self.assertTrue(all(action.executable for action in actions))
first = self.provider.execute_erasure(
self.session,
tenant_id="tenant-1",
subject=direct_subject,
actions=actions,
request_id="dsar-1",
)
second = self.provider.execute_erasure(
self.session,
tenant_id="tenant-1",
subject=direct_subject,
actions=actions,
request_id="dsar-1-retry",
)
self.assertTrue(all(result.status == "executed" for result in first))
self.assertTrue(all(result.status == "unchanged" for result in second))
self.assertIsNone(self.session.get(SearchIndexDocument, "document-1"))
self.assertIsNone(self.session.get(SearchIndexChangeQueue, "change-1"))
acl_subject = DsarSubjectRef(account_id="account-1")
acl_records = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=acl_subject,
)
acl_actions = self.provider.plan_erasure(
self.session,
tenant_id="tenant-1",
subject=acl_subject,
records=acl_records,
)
self.assertTrue(all(action.kind == "manual_review" for action in acl_actions))
self.assertTrue(all(not action.executable for action in acl_actions))
results = self.provider.execute_erasure(
self.session,
tenant_id="tenant-1",
subject=acl_subject,
actions=acl_actions,
request_id="dsar-2",
)
self.assertTrue(all(result.status == "blocked" for result in results))
def test_foreign_records_and_actions_are_rejected(self) -> None:
subject = DsarSubjectRef(external_references={"cases.case": "case-1"})
with self.assertRaisesRegex(ValueError, "foreign provider record"):
self.provider.plan_erasure(
self.session,
tenant_id="tenant-1",
subject=subject,
records=(
DsarRecordRef(
provider_id="cases",
module_id="cases",
resource_type="case",
resource_id="case-1",
category="case",
title="Case",
),
),
)
with self.assertRaisesRegex(ValueError, "foreign provider action"):
self.provider.execute_erasure(
self.session,
tenant_id="tenant-1",
subject=subject,
actions=(
DsarErasureActionRef(
action_id="cases:delete:case:case-1",
provider_id="cases",
module_id="cases",
kind="delete",
resource_type="case",
resource_id="case-1",
title="Delete case",
rationale="Foreign",
executable=True,
),
),
request_id="dsar-1",
)
def test_core_workflow_reports_active_and_inactive_provider(self) -> None:
row = create_data_subject_request(
self.session,
tenant_id="tenant-1",
reference="DSAR-SEARCH-1",
request_kind="access_and_erasure",
subject=DsarSubjectRef(external_references={"cases.case": "case-1"}),
purpose="Respond to a verified request.",
legal_basis="Article 15 and 17 GDPR",
due_at=None,
requested_by_account_id="privacy-officer",
)
self.session.commit()
search_data_subject_request(
self.session,
registry=_Registry(self.provider),
row=row,
expected_revision=1,
)
self.assertEqual(
[SEARCH_DSAR_CAPABILITY], row.coverage["provider_capabilities"]
)
self.assertEqual(2, row.search_result["record_count"])
inactive = create_data_subject_request(
self.session,
tenant_id="tenant-1",
reference="DSAR-SEARCH-2",
request_kind="access",
subject=DsarSubjectRef(external_references={"cases.case": "case-1"}),
purpose="Respond to a verified request.",
legal_basis="Article 15 GDPR",
due_at=None,
requested_by_account_id="privacy-officer",
)
self.session.commit()
search_data_subject_request(
self.session,
registry=_Registry(self.provider, active=False),
row=inactive,
expected_revision=1,
)
self.assertEqual([], inactive.coverage["provider_capabilities"])
self.assertEqual(
[SEARCH_DSAR_CAPABILITY],
inactive.coverage["inactive_provider_capabilities"],
)
self.assertEqual(0, inactive.search_result["record_count"])
def test_manifest_registers_and_documents_the_capability(self) -> None:
self.assertIn(SEARCH_DSAR_CAPABILITY, manifest.capability_factories)
self.assertIn(SEARCH_DSAR_CAPABILITY, manifest.capability_documentation)
self.assertIn(
SEARCH_DSAR_CAPABILITY,
{item.name for item in manifest.provides_interfaces},
)
self.assertTrue(
any(
topic.id == "search.data-subject-requests"
and {"admin", "user"}.issubset(topic.documentation_types)
for topic in manifest.documentation
)
)
if __name__ == "__main__":
unittest.main()