feat(dataflow): add governed DSAR coverage

This commit is contained in:
2026-08-21 03:26:42 +02:00
parent d12e0bce7d
commit 6767905cbb
5 changed files with 1464 additions and 13 deletions
+546
View File
@@ -0,0 +1,546 @@
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_dataflow.backend.db.models import (
DataflowPipeline,
DataflowPipelineDeployment,
DataflowPipelineRevision,
DataflowReconciliationDecision,
DataflowReconciliationDecisionSet,
DataflowRun,
DataflowTrigger,
DataflowTriggerDelivery,
)
from govoplan_dataflow.backend.dsar_provider import (
DATAFLOW_DSAR_CAPABILITY,
DataflowDsarProvider,
)
from govoplan_dataflow.backend.manifest import manifest
NOW = datetime(2026, 8, 21, 20, 0, tzinfo=UTC)
SECRET = "private-dataflow-detail-do-not-export"
class _Registry:
def __init__(self, provider: DataflowDsarProvider, *, active: bool = True) -> None:
self.provider = provider
self.active = active
def capability_names(self):
return (DATAFLOW_DSAR_CAPABILITY,)
def capability_owner(self, name):
self._assert_capability(name)
return "dataflow"
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": ("dataflow",) 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": "dataflow"})(),)
@staticmethod
def _assert_capability(name: str) -> None:
if name != DATAFLOW_DSAR_CAPABILITY:
raise KeyError(name)
class DataflowDsarProviderTests(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 = DataflowDsarProvider()
self.assertIsInstance(self.provider, DsarProvider)
self._seed()
self.session.commit()
def tearDown(self) -> None:
self.session.close()
self.engine.dispose()
def _seed(self) -> None:
pipeline = DataflowPipeline(
id="pipeline-1",
tenant_id="tenant-1",
scope_type="tenant",
definition_kind="flow",
name=SECRET,
description=SECRET,
status="active",
current_revision=1,
created_by="account-1",
updated_by="account-1",
metadata_={"secret": SECRET},
derivation_provenance={"secret": SECRET},
)
other = DataflowPipeline(
id="pipeline-other",
tenant_id="tenant-2",
scope_type="tenant",
definition_kind="flow",
name=SECRET,
status="active",
current_revision=1,
created_by="account-1",
updated_by="account-1",
)
self.session.add_all((pipeline, other))
self.session.flush()
revision = DataflowPipelineRevision(
id="revision-1",
tenant_id="tenant-1",
pipeline_id=pipeline.id,
revision=1,
schema_version=1,
graph={"secret": SECRET},
sql_text=SECRET,
editor_mode="graph",
content_hash="a" * 64,
created_by="account-1",
)
self.session.add(revision)
self.session.flush()
decision_set = DataflowReconciliationDecisionSet(
id="decision-set-1",
tenant_id="tenant-1",
pipeline_id=pipeline.id,
name=SECRET,
node_id="reconcile",
created_by="account-1",
updated_by="account-1",
)
self.session.add(decision_set)
self.session.flush()
run = DataflowRun(
id="run-1",
tenant_id="tenant-1",
pipeline_id=pipeline.id,
pipeline_revision_id=revision.id,
run_type="execute",
status="succeeded",
execution_backend="python",
environment="production",
executor_version="dataflow-v1",
definition_hash="b" * 64,
idempotency_key=SECRET,
request_hash="c" * 64,
request_={"secret": SECRET},
invocation_kind="manual",
correlation_id=SECRET,
causation_id=SECRET,
source_fingerprints=[{"secret": SECRET}],
result_schema=[{"secret": SECRET}],
diagnostics=[{"secret": SECRET}],
input_row_count=1,
output_row_count=1,
output_publication_ref=SECRET,
output_datasource_ref=SECRET,
output_materialization_ref=SECRET,
attempts=1,
progress_percent=100,
progress_phase="complete",
retention_until=NOW + timedelta(days=30),
authorization_={"submitted_principal": {"secret": SECRET}},
resource_budget={"secret": SECRET},
started_at=NOW,
finished_at=NOW,
error=SECRET,
created_by="account-1",
)
trigger = DataflowTrigger(
id="trigger-1",
tenant_id="tenant-1",
pipeline_id=pipeline.id,
pipeline_revision_id=revision.id,
name=SECRET,
kind="event",
status="active",
revision=1,
config_={"secret": SECRET},
publication_={"secret": SECRET},
row_limit=100,
catch_up_policy="coalesce",
max_concurrent_runs=1,
next_fire_at=NOW + timedelta(hours=1),
last_error=SECRET,
authorization_account_id="account-1",
authorization_membership_id="membership-1",
authorization_ref=SECRET,
grant_scopes=[SECRET],
created_by="account-1",
updated_by="account-1",
)
self.session.add_all(
(
DataflowReconciliationDecision(
id="decision-1",
tenant_id="tenant-1",
decision_set_id=decision_set.id,
revision=1,
key_hash="d" * 64,
input_hash="e" * 64,
action="correct",
reason=SECRET,
correction={"secret": SECRET},
actor_ref="account-1",
decided_at=NOW,
),
run,
DataflowPipelineDeployment(
id="deployment-1",
tenant_id="tenant-1",
pipeline_id=pipeline.id,
pipeline_revision_id=revision.id,
environment="production",
source_environment="staging",
status="active",
provenance={"secret": SECRET},
promoted_by="account-1",
),
trigger,
)
)
self.session.flush()
self.session.add(
DataflowTriggerDelivery(
id="delivery-1",
tenant_id="tenant-1",
trigger_id=trigger.id,
pipeline_id=pipeline.id,
pipeline_revision_id=revision.id,
source_key=SECRET,
invocation_kind="event",
status="succeeded",
scheduled_for=NOW,
event_={"secret": SECRET},
run_id=run.id,
attempts=1,
authorization_provenance={"secret": SECRET},
error=SECRET,
finished_at=NOW,
)
)
def test_canonical_selector_is_minimized_and_marks_automation_authority(
self,
) -> None:
records = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=DsarSubjectRef(
account_id="account-1",
membership_id="membership-1",
),
)
self.assertEqual(7, len(records))
trigger = next(
item for item in records if item.resource_type == "dataflow_trigger"
)
self.assertEqual("dataflow_automation_authority", trigger.category)
exported = json.dumps([record.to_dict() for record in records])
self.assertNotIn(SECRET, exported)
self.assertNotIn("account-1", exported)
self.assertNotIn("membership-1", exported)
self.assertNotIn("pipeline-other", exported)
def test_exact_pipeline_package_is_review_only_and_minimized(self) -> None:
records = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=DsarSubjectRef(
account_id="account-1",
external_references={"dataflow.pipeline": "pipeline:pipeline-1"},
),
)
self.assertEqual(8, len(records))
exported = json.dumps([record.to_dict() for record in records])
self.assertNotIn(SECRET, exported)
actions = self.provider.plan_erasure(
self.session,
tenant_id="tenant-1",
subject=DsarSubjectRef(
external_references={"dataflow.pipeline": "pipeline-1"}
),
records=records,
)
self.assertEqual({"manual_review"}, {action.kind for action in actions})
def test_every_exact_reference_and_fail_closed_correlation(self) -> None:
references = {
"dataflow.pipeline_revision": "revision-1",
"dataflow.decision_set": "decision-set-1",
"dataflow.decision": "decision-1",
"dataflow.run": "dataflow-run:run-1",
"dataflow.deployment": "deployment-1",
"dataflow.trigger": "trigger-1",
"dataflow.trigger_delivery": "delivery-1",
}
for key, value in references.items():
with self.subTest(key=key):
records = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=DsarSubjectRef(external_references={key: value}),
)
self.assertEqual(1, len(records))
mismatch = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=DsarSubjectRef(
account_id="account-2",
external_references={"dataflow.run": "run-1"},
),
)
wrong_tenant = self.provider.search_subject(
self.session,
tenant_id="tenant-2",
subject=DsarSubjectRef(external_references={"dataflow.run": "run-1"}),
)
conflict = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=DsarSubjectRef(
external_references={
"dataflow.pipeline_revision": "revision-1",
"dataflow.revision": "different",
}
),
)
self.assertEqual((), mismatch)
self.assertEqual((), wrong_tenant)
self.assertEqual((), conflict)
def test_terminal_run_and_delivery_minimization_is_idempotent(self) -> None:
subject = DsarSubjectRef(
external_references={
"dataflow.run": "run-1",
"dataflow.delivery": "delivery-1",
}
)
records = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=subject,
)
actions = self.provider.plan_erasure(
self.session,
tenant_id="tenant-1",
subject=subject,
records=records,
)
self.assertEqual({"anonymize"}, {action.kind for action in actions})
first = self.provider.execute_erasure(
self.session,
tenant_id="tenant-1",
subject=subject,
actions=actions,
request_id="dsar-1",
)
second = self.provider.execute_erasure(
self.session,
tenant_id="tenant-1",
subject=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))
run = self.session.get(DataflowRun, "run-1")
delivery = self.session.get(DataflowTriggerDelivery, "delivery-1")
self.assertEqual({}, run.request_)
self.assertEqual([], run.diagnostics)
self.assertIsNotNone(run.purged_at)
self.assertIsNone(delivery.event_)
self.assertEqual({}, delivery.authorization_provenance)
self.assertEqual(SECRET, delivery.source_key)
def test_automation_authority_is_revoked_with_retry_support(self) -> None:
subject = DsarSubjectRef(
account_id="account-1",
membership_id="membership-1",
)
records = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=subject,
)
actions = self.provider.plan_erasure(
self.session,
tenant_id="tenant-1",
subject=subject,
records=records,
)
trigger_action = next(
action for action in actions if action.resource_type == "dataflow_trigger"
)
self.assertEqual("revoke", trigger_action.kind)
self.assertTrue(trigger_action.executable)
first = self.provider.execute_erasure(
self.session,
tenant_id="tenant-1",
subject=subject,
actions=(trigger_action,),
request_id="dsar-2",
)
second = self.provider.execute_erasure(
self.session,
tenant_id="tenant-1",
subject=subject,
actions=(trigger_action,),
request_id="dsar-2-retry",
)
self.assertEqual("executed", first[0].status)
self.assertEqual("unchanged", second[0].status)
trigger = self.session.get(DataflowTrigger, "trigger-1")
self.assertEqual("disabled", trigger.status)
self.assertEqual("redacted", trigger.authorization_account_id)
self.assertEqual("redacted", trigger.authorization_membership_id)
self.assertEqual([], trigger.grant_scopes)
self.assertEqual({}, trigger.config_)
def test_foreign_records_and_actions_are_rejected(self) -> None:
subject = DsarSubjectRef(account_id="account-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-3",
)
def test_core_workflow_reports_active_and_inactive_provider(self) -> None:
row = create_data_subject_request(
self.session,
tenant_id="tenant-1",
reference="DSAR-DATAFLOW-1",
request_kind="access_and_erasure",
subject=DsarSubjectRef(account_id="account-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(
[DATAFLOW_DSAR_CAPABILITY],
row.coverage["provider_capabilities"],
)
self.assertEqual(7, row.search_result["record_count"])
inactive = create_data_subject_request(
self.session,
tenant_id="tenant-1",
reference="DSAR-DATAFLOW-2",
request_kind="access",
subject=DsarSubjectRef(account_id="account-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(
[DATAFLOW_DSAR_CAPABILITY],
inactive.coverage["inactive_provider_capabilities"],
)
self.assertEqual(0, inactive.search_result["record_count"])
def test_manifest_registers_and_documents_capability(self) -> None:
self.assertIn(DATAFLOW_DSAR_CAPABILITY, manifest.capability_factories)
self.assertIn(DATAFLOW_DSAR_CAPABILITY, manifest.capability_documentation)
self.assertIn(
DATAFLOW_DSAR_CAPABILITY,
{item.name for item in manifest.provides_interfaces},
)
self.assertTrue(
any(
topic.id == "dataflow.data-subject-requests"
and {"admin", "user"}.issubset(topic.documentation_types)
for topic in manifest.documentation
)
)
if __name__ == "__main__":
unittest.main()