Files
govoplan-addresses/tests/test_tabular_imports.py
zemion d4fa024034
Module Package Release / publish-packages (push) Successful in 14s
fix(addresses): preserve complete import rollback evidence and batch previews
Release v0.1.23. Coordinated integrity review: GovOPlaN/govoplan-core#298.
2026-09-08 12:19:36 +02:00

623 lines
27 KiB
Python

from __future__ import annotations
import base64
from io import BytesIO
import unittest
from unittest.mock import patch
from sqlalchemy import create_engine, event
from sqlalchemy.orm import sessionmaker
from openpyxl import Workbook
from govoplan_addresses.backend.db.models import AddressBook, AddressList, AddressListEntry, Contact, ContactEmail, ContactPhone, ContactPostalAddress
from govoplan_addresses.backend.import_schemas import (
AddressImportConfiguration,
AddressImportPreviewRequest,
AddressImportProfileCreateRequest,
AddressImportProfileUpdateRequest,
AddressImportRollbackRequest,
)
from govoplan_addresses.backend.imports import (
apply_address_import,
_contact_hash,
_contact_snapshot,
create_import_profile,
get_import_run,
import_run_payload,
preview_address_import,
rollback_address_import,
update_import_profile,
)
from govoplan_core.db.base import Base
from govoplan_addresses.backend.service import delete_contact
class Principal:
account_id = "account-1"
group_ids = frozenset({"group-1"})
@property
def tenant_id(self) -> str:
return "tenant-1"
def has(self, scope: str) -> bool:
return scope in {
"addresses:address_book:read",
"addresses:address_book:write",
"addresses:contact:read",
"addresses:contact:write",
}
class OtherTenantPrincipal(Principal):
@property
def tenant_id(self) -> str:
return "tenant-2"
def encoded(value: str) -> str:
return base64.b64encode(value.encode()).decode()
class AddressTabularImportTests(unittest.TestCase):
def setUp(self) -> None:
engine = create_engine("sqlite+pysqlite:///:memory:")
Base.metadata.create_all(engine)
self.session = sessionmaker(bind=engine, expire_on_commit=False)()
self.principal = Principal()
self.book = AddressBook(
tenant_id="tenant-1",
scope_type="tenant",
scope_id="tenant-1",
name="Imported contacts",
source_kind="local",
read_only=False,
)
self.session.add(self.book)
self.profile = create_import_profile(
self.session,
self.principal,
AddressImportProfileCreateRequest(
scope_type="tenant",
name="Monthly contacts",
source_format="csv",
configuration=AddressImportConfiguration(
delimiter=";",
field_mappings={
"source_key": "id",
"given_name": "first",
"family_name": "last",
"email": "email",
"organization": "organization",
},
),
),
)
self.session.flush()
def _preview_rows(self, count: int = 1, *, organization: str = "Office"):
return preview_address_import(
self.session, self.principal, self.book.id,
AddressImportPreviewRequest(
profile_id=self.profile.id, filename="fixture.csv",
content_base64=encoded(
"id;first;last;email;organization\n"
+ "".join(f"{index};Given;Family;u{index}@example.test;{organization}\n" for index in range(count))
),
),
)
def _apply(self, run):
apply_address_import(self.session, self.principal, run.id, expected_plan_hash=run.plan_hash)
self.session.commit()
def test_rollback_restores_previously_deleted_state_and_source_fields(self) -> None:
self._apply(self._preview_rows())
contact = self.session.query(Contact).one()
delete_contact(self.session, self.principal, contact.id)
self.session.commit()
prior_deleted_at = contact.deleted_at
prior_source_revision = contact.source_revision
run = self._preview_rows(organization="Changed")
self._apply(run)
self.assertIsNone(contact.deleted_at)
before = run.result_evidence["updated_contacts"][0]["before"]
self.assertEqual(2, before["version"])
self.assertEqual(prior_deleted_at.isoformat(), before["deleted_at"])
rollback_address_import(
self.session, self.principal, run.id,
AddressImportRollbackRequest(expected_plan_hash=run.plan_hash, reason="Restore the reviewed previous state."),
)
self.session.commit()
self.assertEqual("rolled_back", run.status)
self.assertEqual(prior_deleted_at, contact.deleted_at)
self.assertEqual("Office", contact.organization)
self.assertEqual(prior_source_revision, contact.source_revision)
def test_rollback_restores_all_point_evidence_and_identities_after_reload(self) -> None:
self._apply(self._preview_rows())
contact = self.session.query(Contact).one()
contact.emails[0].original_email = " U0@EXAMPLE.TEST "
contact.emails[0].provenance = {"nested": {"original": "email evidence"}}
contact.note = " Exact retained note\r\n"
contact.tags = ["Exact", "Exact", " padded "]
contact.metadata_ = None
contact.phones.append(ContactPhone(
phone="+49 123", original_phone=" +49 (123) ", normalized_phone="+49123",
provenance={"original": "phone evidence"}, label="Office", is_primary=True, order_index=4,
))
contact.postal_addresses.append(ContactPostalAddress(
street="Main Street", original_value={"street": " Main Street "},
normalized_value={"street": "main street"}, provenance={"original": "postal evidence"},
is_primary=True, order_index=7,
))
self.session.commit()
before = _contact_snapshot(contact)["points"]
run = self._preview_rows(organization="Changed")
self._apply(run)
self.assertEqual(before["emails"], _contact_snapshot(contact)["points"]["emails"])
self.session.expire_all()
rollback_address_import(
self.session, self.principal, run.id,
AddressImportRollbackRequest(expected_plan_hash=run.plan_hash, reason="Restore all original point evidence."),
)
self.session.commit()
self.session.expire_all()
self.assertEqual(before, _contact_snapshot(contact)["points"])
self.assertEqual(" Exact retained note\r\n", contact.note)
self.assertEqual(["Exact", "Exact", " padded "], contact.tags)
self.assertIsNone(contact.metadata_)
def test_post_import_point_provenance_edit_is_guarded(self) -> None:
self._apply(self._preview_rows())
run = self._preview_rows(organization="Changed")
self._apply(run)
contact = self.session.query(Contact).one()
after_hash = _contact_hash(contact)
contact.emails[0].provenance = {"later": "manual evidence"}
self.session.commit()
self.assertNotEqual(after_hash, _contact_hash(contact))
with self.assertRaisesRegex(ValueError, "changed after import"):
rollback_address_import(
self.session, self.principal, run.id,
AddressImportRollbackRequest(expected_plan_hash=run.plan_hash, reason="Do not erase a later point edit."),
)
self.assertEqual({"later": "manual evidence"}, contact.emails[0].provenance)
def test_point_lock_order_does_not_change_tied_collection_order_or_reviewed_hash(self) -> None:
self._apply(self._preview_rows())
contact = self.session.query(Contact).one()
contact.emails.append(ContactEmail(
id="00000000-0000-0000-0000-000000000000", email="extra@example.test",
original_email="extra@example.test", normalized_email="extra@example.test",
label="Extra", is_primary=False, order_index=0,
))
self.session.commit()
self.session.expire_all()
before = _contact_snapshot(contact)["points"]
run = self._preview_rows(organization="Changed")
self._apply(run)
rollback_address_import(
self.session, self.principal, run.id,
AddressImportRollbackRequest(expected_plan_hash=run.plan_hash, reason="Preserve tied contact-point ordering."),
)
self.session.commit()
self.session.expire_all()
self.assertEqual(before, _contact_snapshot(contact)["points"])
def _link_email(self, contact):
address_list = AddressList(address_book_id=self.book.id, tenant_id="tenant-1", name="Recipients")
entry = AddressListEntry(address_list=address_list, contact=contact, contact_email=contact.emails[0], target_kind="email")
self.session.add(entry)
self.session.commit()
return entry
def test_unchanged_point_keeps_address_list_identity_through_apply_and_rollback(self) -> None:
self._apply(self._preview_rows())
contact = self.session.query(Contact).one()
entry = self._link_email(contact)
point_id = contact.emails[0].id
run = self._preview_rows(organization="Changed")
self._apply(run)
self.session.expire_all()
self.assertEqual(point_id, entry.contact_email_id)
self.assertEqual(point_id, contact.emails[0].id)
rollback_address_import(
self.session, self.principal, run.id,
AddressImportRollbackRequest(expected_plan_hash=run.plan_hash, reason="Keep the explicit recipient reference."),
)
self.session.commit()
self.session.expire_all()
self.assertEqual(point_id, entry.contact_email_id)
self.assertEqual(point_id, contact.emails[0].id)
def test_replacing_a_linked_point_requires_reconciliation_before_contact_mutation(self) -> None:
self._apply(self._preview_rows())
contact = self.session.query(Contact).one()
entry = self._link_email(contact)
run = preview_address_import(
self.session, self.principal, self.book.id,
AddressImportPreviewRequest(profile_id=self.profile.id, filename="fixture.csv", content_base64=encoded(
"id;first;last;email;organization\n0;Given;Family;different@example.test;Changed\n"
)),
)
before = _contact_hash(contact)
with self.assertRaisesRegex(ValueError, "address-list or governance references"):
apply_address_import(self.session, self.principal, run.id, expected_plan_hash=run.plan_hash)
self.assertEqual(before, _contact_hash(contact))
self.assertEqual(contact.emails[0].id, entry.contact_email_id)
self.assertEqual("previewed", run.status)
def test_new_reference_to_imported_point_blocks_destructive_rollback(self) -> None:
self._apply(self._preview_rows())
run = preview_address_import(
self.session, self.principal, self.book.id,
AddressImportPreviewRequest(profile_id=self.profile.id, filename="fixture.csv", content_base64=encoded(
"id;first;last;email;organization\n0;Given;Family;different@example.test;Changed\n"
)),
)
self._apply(run)
contact = self.session.query(Contact).one()
entry = self._link_email(contact)
before = _contact_hash(contact)
with self.assertRaisesRegex(ValueError, "address-list or governance references"):
rollback_address_import(
self.session, self.principal, run.id,
AddressImportRollbackRequest(expected_plan_hash=run.plan_hash, reason="Retain the newly referenced recipient point."),
)
self.assertEqual(before, _contact_hash(contact))
self.assertEqual(contact.emails[0].id, entry.contact_email_id)
self.assertEqual("applied", run.status)
def test_version_one_point_incomplete_evidence_is_not_accepted(self) -> None:
import copy
self._apply(self._preview_rows())
run = self._preview_rows(organization="Changed")
self._apply(run)
evidence = copy.deepcopy(run.result_evidence)
evidence["updated_contacts"][0]["before"]["version"] = 1
run.result_evidence = evidence
self.session.commit()
with self.assertRaisesRegex(ValueError, "incomplete legacy rollback evidence"):
rollback_address_import(
self.session, self.principal, run.id,
AddressImportRollbackRequest(expected_plan_hash=run.plan_hash, reason="Do not infer missing point evidence."),
)
def test_legacy_or_incomplete_before_images_fail_before_any_rollback_mutation(self) -> None:
self._apply(self._preview_rows())
run = self._preview_rows(2, organization="Changed")
self._apply(run)
evidence = dict(run.result_evidence)
updates = [dict(item) for item in evidence["updated_contacts"]]
updates[0]["before"] = updates[0]["before"]["contact"]
evidence["updated_contacts"] = updates
run.result_evidence = evidence
self.session.commit()
with self.assertRaisesRegex(ValueError, "incomplete legacy rollback evidence"):
rollback_address_import(
self.session, self.principal, run.id,
AddressImportRollbackRequest(expected_plan_hash=run.plan_hash, reason="Reject an incomplete previous state."),
)
self.assertEqual("applied", run.status)
self.assertEqual(2, self.session.query(Contact).filter(Contact.deleted_at.is_(None)).count())
self.assertTrue(all(contact.organization == "Changed" for contact in self.session.query(Contact)))
def test_preview_queries_are_batched_and_relationships_are_eager(self) -> None:
queries = []
def capture(conn, cursor, statement, parameters, context, executemany):
if statement.lstrip().upper().startswith("SELECT"):
queries.append(statement)
event.listen(self.session.bind, "before_cursor_execute", capture)
try:
first = self._preview_rows(50)
self.assertEqual(50, first.statistics["create"])
self.assertLessEqual(len(queries), 3)
self._apply(first)
self.session.expunge_all()
queries.clear()
repeat = self._preview_rows(50)
self.assertEqual(50, repeat.statistics["unchanged"])
self.assertLessEqual(len(queries), 6)
finally:
event.remove(self.session.bind, "before_cursor_execute", capture)
def test_preview_batches_preserve_first_source_match_and_book_scope(self) -> None:
self._apply(self._preview_rows(5))
original = self.session.query(Contact).order_by(Contact.created_at, Contact.id).first()
other_book = AddressBook(tenant_id="tenant-1", scope_type="tenant", scope_id="tenant-1", name="Other", source_kind="local", read_only=False)
self.session.add(other_book)
self.session.flush()
self.session.add_all([
Contact(tenant_id="tenant-1", address_book_id=original.address_book_id, display_name="Later duplicate", source_ref=original.source_ref),
Contact(tenant_id="tenant-1", address_book_id=other_book.id, display_name="Other book", source_ref=original.source_ref),
])
self.session.commit()
with patch("govoplan_addresses.backend.imports.CONTACT_LOOKUP_BATCH_SIZE", 2):
repeat = self._preview_rows(5)
self.assertEqual(5, repeat.statistics["unchanged"])
def test_missing_created_after_hash_blocks_rollback(self) -> None:
run = self._preview_rows()
self._apply(run)
run.plan_data = [{key: value for key, value in item.items() if key != "after_hash"} for item in run.plan_data]
self.session.commit()
with self.assertRaisesRegex(ValueError, "evidence is incomplete"):
rollback_address_import(
self.session, self.principal, run.id,
AddressImportRollbackRequest(expected_plan_hash=run.plan_hash, reason="Incomplete evidence must not delete contacts."),
)
self.assertEqual(1, self.session.query(Contact).filter(Contact.deleted_at.is_(None)).count())
def test_applied_effect_hashes_survive_commit_and_reload(self) -> None:
run = self._preview_rows()
self._apply(run)
run_id, plan_hash = run.id, run.plan_hash
self.session.expunge_all()
reloaded = get_import_run(self.session, self.principal, run_id)
self.assertTrue(reloaded.plan_data[0]["contact_id"])
self.assertEqual(64, len(reloaded.plan_data[0]["after_hash"]))
rollback_address_import(
self.session, self.principal, run_id,
AddressImportRollbackRequest(expected_plan_hash=plan_hash, reason="Durable after-images guard rollback."),
)
self.session.commit()
self.assertEqual(0, self.session.query(Contact).filter(Contact.deleted_at.is_(None)).count())
def test_replayed_apply_still_requires_the_reviewed_plan_hash(self) -> None:
run = self._preview_rows()
self._apply(run)
with self.assertRaisesRegex(ValueError, "reviewed import plan changed"):
apply_address_import(self.session, self.principal, run.id, expected_plan_hash="0" * 64)
def test_rollback_rejects_a_moved_target_without_archiving_it(self) -> None:
run = self._preview_rows()
self._apply(run)
other_book = AddressBook(tenant_id="tenant-1", scope_type="tenant", scope_id="tenant-1", name="Other", source_kind="local", read_only=False)
self.session.add(other_book)
self.session.flush()
contact = self.session.query(Contact).one()
contact.address_book_id = other_book.id
self.session.commit()
with self.assertRaisesRegex(ValueError, "moved to another address book"):
rollback_address_import(
self.session, self.principal, run.id,
AddressImportRollbackRequest(expected_plan_hash=run.plan_hash, reason="Moved contacts require manual reconciliation."),
)
self.assertIsNone(contact.deleted_at)
self.assertEqual("applied", run.status)
def test_rollback_retains_post_import_edits(self) -> None:
run = self._preview_rows()
self._apply(run)
contact = self.session.query(Contact).one()
contact.organization = "Later manual edit"
self.session.commit()
with self.assertRaisesRegex(ValueError, "changed after import"):
rollback_address_import(
self.session, self.principal, run.id,
AddressImportRollbackRequest(expected_plan_hash=run.plan_hash, reason="Later changes must remain untouched."),
)
self.assertIsNone(contact.deleted_at)
self.assertEqual("Later manual edit", contact.organization)
def test_preview_apply_repeat_and_guarded_rollback(self) -> None:
payload = AddressImportPreviewRequest(
profile_id=self.profile.id,
filename="contacts.csv",
content_base64=encoded(
"id;first;last;email;organization\n"
"1;Ada;Lovelace;ada@example.test;Analysis Office\n"
"2;Grace;Hopper;grace@example.test;Computing Office\n"
),
)
run = preview_address_import(self.session, self.principal, self.book.id, payload)
self.assertEqual(2, run.statistics["create"])
self.assertFalse(run.diagnostics)
applied = apply_address_import(
self.session,
self.principal,
run.id,
expected_plan_hash=run.plan_hash,
)
self.assertEqual("applied", applied.status)
self.assertEqual(2, self.session.query(Contact).filter(Contact.deleted_at.is_(None)).count())
self.assertIs(applied, apply_address_import(self.session, self.principal, run.id, expected_plan_hash=run.plan_hash))
response_evidence = import_run_payload(applied)["result_evidence"]
self.assertEqual(2, response_evidence["created_contact_count"])
self.assertNotIn("created_contact_ids", response_evidence)
self.assertNotIn("updated_contacts", response_evidence)
repeated = preview_address_import(self.session, self.principal, self.book.id, payload)
self.assertEqual(2, repeated.statistics["unchanged"])
apply_address_import(self.session, self.principal, repeated.id, expected_plan_hash=repeated.plan_hash)
self.assertEqual(2, self.session.query(Contact).filter(Contact.deleted_at.is_(None)).count())
rolled_back = rollback_address_import(
self.session,
self.principal,
run.id,
AddressImportRollbackRequest(
expected_plan_hash=run.plan_hash,
reason="The operator selected the wrong monthly file.",
),
)
self.assertEqual("rolled_back", rolled_back.status)
self.assertEqual(0, self.session.query(Contact).filter(Contact.deleted_at.is_(None)).count())
def test_rollback_rejects_a_stale_review_hash(self) -> None:
run = preview_address_import(
self.session,
self.principal,
self.book.id,
AddressImportPreviewRequest(
profile_id=self.profile.id,
filename="contacts.csv",
content_base64=encoded(
"id;first;last;email;organization\n"
"1;Ada;Lovelace;ada@example.test;Analysis Office\n"
),
),
)
apply_address_import(
self.session,
self.principal,
run.id,
expected_plan_hash=run.plan_hash,
)
with self.assertRaisesRegex(ValueError, "reviewed import plan changed"):
rollback_address_import(
self.session,
self.principal,
run.id,
AddressImportRollbackRequest(
expected_plan_hash="0" * 64,
reason="The operator selected the wrong monthly file.",
),
)
def test_persisted_run_read_is_tenant_bounded_and_source_safe(self) -> None:
source = "id;first;last;email;organization\n1;Ada;Lovelace;ada@example.test;Analysis Office\n"
run = preview_address_import(
self.session,
self.principal,
self.book.id,
AddressImportPreviewRequest(
profile_id=self.profile.id,
filename="contacts.csv",
content_base64=encoded(source),
),
)
self.session.flush()
payload = import_run_payload(get_import_run(self.session, self.principal, run.id))
self.assertEqual("previewed", payload["status"])
self.assertEqual(run.plan_hash, payload["plan_hash"])
self.assertNotIn("plan_data", payload)
self.assertNotIn(source, repr(payload))
with self.assertRaisesRegex(ValueError, "not found"):
get_import_run(self.session, OtherTenantPrincipal(), run.id)
def test_duplicate_keys_and_changed_targets_block_apply(self) -> None:
duplicate = preview_address_import(
self.session,
self.principal,
self.book.id,
AddressImportPreviewRequest(
profile_id=self.profile.id,
filename="duplicates.csv",
content_base64=encoded(
"id;first;last;email;organization\n"
"1;Ada;Lovelace;ada@example.test;One\n"
"1;Ada;Lovelace;ada@example.test;Two\n"
),
),
)
self.assertEqual(2, duplicate.statistics["conflict"])
with self.assertRaisesRegex(ValueError, "error diagnostics"):
apply_address_import(self.session, self.principal, duplicate.id, expected_plan_hash=duplicate.plan_hash)
initial = preview_address_import(
self.session,
self.principal,
self.book.id,
AddressImportPreviewRequest(
profile_id=self.profile.id,
filename="one.csv",
content_base64=encoded("id;first;last;email;organization\n1;Ada;Lovelace;ada@example.test;One\n"),
),
)
apply_address_import(self.session, self.principal, initial.id, expected_plan_hash=initial.plan_hash)
changed = preview_address_import(
self.session,
self.principal,
self.book.id,
AddressImportPreviewRequest(
profile_id=self.profile.id,
filename="one.csv",
content_base64=encoded("id;first;last;email;organization\n1;Ada;Lovelace;ada@example.test;Two\n"),
),
)
contact = self.session.query(Contact).filter(Contact.deleted_at.is_(None)).one()
contact.organization = "Concurrent edit"
self.session.flush()
with self.assertRaisesRegex(ValueError, "changed after preview"):
apply_address_import(self.session, self.principal, changed.id, expected_plan_hash=changed.plan_hash)
def test_profile_updates_create_immutable_versions(self) -> None:
next_profile = update_import_profile(
self.session,
self.principal,
self.profile.id,
payload=AddressImportProfileUpdateRequest(name="Monthly contacts v2"),
)
self.assertFalse(self.profile.is_current)
self.assertTrue(next_profile.is_current)
self.assertEqual(self.profile.profile_key, next_profile.profile_key)
self.assertEqual(2, next_profile.version)
def test_xlsx_sheet_selection_and_formula_rejection(self) -> None:
workbook = Workbook()
workbook.active.title = "Ignore"
sheet = workbook.create_sheet("Contacts")
sheet.append(["id", "first", "last", "email", "organization"])
sheet.append(["1", "Ada", "Lovelace", "ada@example.test", "Analysis Office"])
content = BytesIO()
workbook.save(content)
xlsx_profile = create_import_profile(
self.session,
self.principal,
AddressImportProfileCreateRequest(
scope_type="tenant",
name="Workbook contacts",
source_format="xlsx",
configuration=AddressImportConfiguration(
sheet_name="Contacts",
field_mappings={
"source_key": "id",
"given_name": "first",
"family_name": "last",
"email": "email",
"organization": "organization",
},
),
),
)
self.session.flush()
run = preview_address_import(
self.session,
self.principal,
self.book.id,
AddressImportPreviewRequest(
profile_id=xlsx_profile.id,
filename="contacts.xlsx",
content_base64=base64.b64encode(content.getvalue()).decode(),
),
)
self.assertEqual(1, run.statistics["create"])
sheet["E2"] = "=CONCAT(\"Analysis\", \" Office\")"
content = BytesIO()
workbook.save(content)
with self.assertRaisesRegex(ValueError, "formulas are never evaluated"):
preview_address_import(
self.session,
self.principal,
self.book.id,
AddressImportPreviewRequest(
profile_id=xlsx_profile.id,
filename="contacts.xlsx",
content_base64=base64.b64encode(content.getvalue()).decode(),
),
)
if __name__ == "__main__":
unittest.main()