junte/Model
1
0
Fork 0
mirror of https://github.com/Hestia-Homes/Model.git synced 2026-06-08 11:17:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

unsanistiesed address list instead of raw address lit

Browse source
This commit is contained in:
Jun-te Kim 2026-05-22 08:27:59 +00:00
parent 91bb4b6571
commit 0dee917094
16 changed files with 107 additions and 109 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
applications/SAL/handler.py
View file

@ -4,10 +4,10 @@ from orchestration.sal_orchestrator import (
SALOrchestrator,
)
from infrastructure.csv_s3_client import CsvS3Client
from repositories.raw_address.raw_address_list_csv_s3_repository import (
RawAddressListCsvS3Repository,
from repositories.unsanitised_address.unsanitised_address_list_csv_s3_repository import (
UnsanitisedAddressListCsvS3Repository,
)
from domain.addresses.raw_address import AddressList
from domain.addresses.unsanitised_address import AddressList
def handler(
@ -24,18 +24,16 @@ def handler(
boto_s3: Any = boto3_client("s3")
csv_client = CsvS3Client(boto_s3, bucket)
raw_address_repo = RawAddressListCsvS3Repository(csv_client, bucket)
unsanitised_address_repo = UnsanitisedAddressListCsvS3Repository(csv_client, bucket)
orchestrator = SALOrchestrator(
raw_address_repo=raw_address_repo,
sal = SALOrchestrator(
unsanitised_address_repo=unsanitised_address_repo,
)
list_of_raw_address: AddressList = orchestrator.get_raw_addresses(
input_s3_uri=s3_uri
)
addressList: AddressList = sal.get_unsanitised_addresses(input_s3_uri=s3_uri)
col_to_desc_map = orchestrator.get_col_to_description_mappings(
list_of_raw_address=list_of_raw_address
col_to_desc_map = sal.get_col_to_description_mappings(
list_of_unsanitised_address=addressList
)
# Read csv of user input

8
applications/postcode_splitter/handler.py
View file

@ -12,8 +12,8 @@ from infrastructure.address2uprn_queue_client import Address2UprnQueueClient
from infrastructure.csv_s3_client import CsvS3Client
from orchestration.postcode_splitter_orchestrator import PostcodeSplitterOrchestrator
from orchestration.task_orchestrator import TaskOrchestrator
from repositories.raw_address.raw_address_list_csv_s3_repository import (
RawAddressListCsvS3Repository,
from repositories.unsanitised_address.unsanitised_address_list_csv_s3_repository import (
UnsanitisedAddressListCsvS3Repository,
)
from utilities.aws_lambda.subtask_handler import subtask_handler
@ -36,12 +36,12 @@ def handler(
boto_sqs: Any = boto3_client("sqs")
csv_client = CsvS3Client(boto_s3, bucket)
user_address_repo = RawAddressListCsvS3Repository(csv_client, bucket)
unsanitised_address_repo = UnsanitisedAddressListCsvS3Repository(csv_client, bucket)
queue_client = Address2UprnQueueClient(boto_sqs, queue_url)
splitter = PostcodeSplitterOrchestrator(
task_orchestrator=task_orchestrator,
user_address_repo=user_address_repo,
unsanitised_address_repo=unsanitised_address_repo,
queue_client=queue_client,
)

6
domain/addresses/postcode_batching.py
View file

@ -2,12 +2,12 @@ from __future__ import annotations
from collections.abc import Iterable, Iterator
from domain.addresses.raw_address import AddressList, RawAddress
from domain.addresses.unsanitised_address import AddressList, UnsanitisedAddress
from domain.postcode import Postcode
def iter_postcode_grouped_batches(
addresses: Iterable[RawAddress],
addresses: Iterable[UnsanitisedAddress],
*,
max_batch_size: int = 500,
) -> Iterator[AddressList]:
@ -43,7 +43,7 @@ def iter_postcode_grouped_batches(
def _group_by_postcode_in_order(
addresses: Iterable[RawAddress],
addresses: Iterable[UnsanitisedAddress],
) -> dict[Postcode, AddressList]:
groups: dict[Postcode, AddressList] = {}
for address in addresses:

4
domain/addresses/raw_address.py → domain/addresses/unsanitised_address.py
View file

@ -11,7 +11,7 @@ def _empty_source_row() -> dict[str, str]:
@dataclass(frozen=True)
class RawAddress:
class UnsanitisedAddress:
address: str
postcode: Postcode
org_reference: Optional[str] = None
@ -21,4 +21,4 @@ class RawAddress:
# A batch of raw, pre-standardisation addresses as supplied by a landlord.
AddressList = NewType("AddressList", list[RawAddress])
AddressList = NewType("AddressList", list[UnsanitisedAddress])

12
orchestration/postcode_splitter_orchestrator.py
View file

@ -5,8 +5,8 @@ from uuid import UUID
from infrastructure.address2uprn_queue_client import Address2UprnQueueClient
from orchestration.task_orchestrator import TaskOrchestrator
from domain.addresses.postcode_batching import iter_postcode_grouped_batches
from repositories.raw_address.raw_address_list_repository import (
RawAddressListRepository,
from repositories.unsanitised_address.unsanitised_address_list_repository import (
UnsanitisedAddressListRepository,
)
@ -14,12 +14,12 @@ class PostcodeSplitterOrchestrator:
def __init__(
self,
task_orchestrator: TaskOrchestrator,
raw_address_repo: RawAddressListRepository,
unsanitised_address_repo: UnsanitisedAddressListRepository,
queue_client: Address2UprnQueueClient,
max_batch_size: int = 500,
) -> None:
self._task_orchestrator = task_orchestrator
self._raw_address_repo = raw_address_repo
self._unsanitised_address_repo = unsanitised_address_repo
self._queue_client = queue_client
self._max_batch_size = max_batch_size
@ -30,7 +30,7 @@ class PostcodeSplitterOrchestrator:
parent_subtask_id: UUID,
input_s3_uri: str,
) -> list[UUID]:
addresses = self._raw_address_repo.load_batch(input_s3_uri)
addresses = self._unsanitised_address_repo.load_batch(input_s3_uri)
path_prefix = (
f"ara_postcode_splitter_batches/{parent_task_id}/{parent_subtask_id}"
)
@ -39,7 +39,7 @@ class PostcodeSplitterOrchestrator:
for batch in iter_postcode_grouped_batches(
addresses, max_batch_size=self._max_batch_size
):
batch_uri = self._raw_address_repo.save_batch(batch, path_prefix)
batch_uri = self._unsanitised_address_repo.save_batch(batch, path_prefix)
child = self._task_orchestrator.create_child_subtask(
parent_task_id,
inputs={

20
orchestration/sal_orchestrator.py
View file

@ -1,25 +1,25 @@
from repositories.raw_address.raw_address_list_repository import (
RawAddressListRepository,
from repositories.unsanitised_address.unsanitised_address_list_repository import (
UnsanitisedAddressListRepository,
)
from domain.addresses.raw_address import AddressList
from domain.addresses.unsanitised_address import AddressList
class SALOrchestrator:
def __init__(self, raw_address_repo: RawAddressListRepository) -> None:
self._raw_address_repo = raw_address_repo
def __init__(self, unsanitised_address_repo: UnsanitisedAddressListRepository) -> None:
self._unsanitised_address_repo = unsanitised_address_repo
def get_raw_addresses(
def get_unsanitised_addresses(
self,
input_s3_uri: str,
) -> AddressList:
return self._raw_address_repo.load_batch(input_s3_uri)
return self._unsanitised_address_repo.load_batch(input_s3_uri)
def get_col_to_description_mappings(
self, list_of_raw_address: AddressList
self, list_of_unsanitised_address: AddressList
) -> dict[str, set[str]]:
mappings: dict[str, set[str]] = {}
for raw_address in list_of_raw_address:
for key, value in raw_address.additional_info.items():
for unsanitised_address in list_of_unsanitised_address:
for key, value in unsanitised_address.additional_info.items():
# Lower-case so case-only typos collapse to one variant.
mappings.setdefault(key, set()).add(value.lower())
return mappings

0
repositories/raw_address/__init__.py → repositories/unsanitised_address/__init__.py
View file

14
repositories/raw_address/raw_address_list_csv_s3_repository.py → repositories/unsanitised_address/unsanitised_address_list_csv_s3_repository.py
View file

@ -4,11 +4,11 @@ import uuid
from datetime import datetime, timezone
from typing import Optional
from domain.addresses.raw_address import AddressList, RawAddress
from domain.addresses.unsanitised_address import AddressList, UnsanitisedAddress
from domain.postcode import Postcode
from infrastructure.csv_s3_client import CsvS3Client
from repositories.raw_address.raw_address_list_repository import (
RawAddressListRepository,
from repositories.unsanitised_address.unsanitised_address_list_repository import (
UnsanitisedAddressListRepository,
)
_ADDRESS_COLUMNS: tuple[str, str, str] = ("Address 1", "Address 2", "Address 3")
@ -17,7 +17,7 @@ _INTERNAL_REFERENCE_COLUMN: str = "Internal Reference"
_POSTCODE_CLEAN_COLUMN: str = "postcode_clean"
class RawAddressListCsvS3Repository(RawAddressListRepository):
class UnsanitisedAddressListCsvS3Repository(UnsanitisedAddressListRepository):
def __init__(self, csv_client: CsvS3Client, bucket: str) -> None:
self._csv_client = csv_client
self._bucket = bucket
@ -36,13 +36,13 @@ class RawAddressListCsvS3Repository(RawAddressListRepository):
for col in _ADDRESS_COLUMNS
if col in row and row[col].strip()
]
raw_address = ", ".join(parts)
unsanitised_address = ", ".join(parts)
postcode = row.get(_POSTCODE_COLUMN, "")
raw_ref = row.get(_INTERNAL_REFERENCE_COLUMN, "").strip()
internal_reference: Optional[str] = raw_ref or None
addresses.append(
RawAddress(
address=raw_address,
UnsanitisedAddress(
address=unsanitised_address,
postcode=Postcode(postcode),
org_reference=internal_reference,
additional_info=row,

4
repositories/raw_address/raw_address_list_repository.py → repositories/unsanitised_address/unsanitised_address_list_repository.py
View file

@ -2,10 +2,10 @@ from __future__ import annotations
from abc import ABC, abstractmethod
from domain.addresses.raw_address import AddressList
from domain.addresses.unsanitised_address import AddressList
class RawAddressListRepository(ABC):
class UnsanitisedAddressListRepository(ABC):
@abstractmethod
def load_batch(self, s3_uri: str) -> AddressList: ...

4
tests/domain/addresses/test_postcode_batching.py
View file

@ -1,14 +1,14 @@
import pytest
from domain.addresses.postcode_batching import iter_postcode_grouped_batches
from domain.addresses.raw_address import AddressList, RawAddress
from domain.addresses.unsanitised_address import AddressList, UnsanitisedAddress
from domain.postcode import Postcode
def _addrs(postcode: str, n: int) -> AddressList:
return AddressList(
[
RawAddress(address=f"{i} {postcode} Street", postcode=Postcode(postcode))
UnsanitisedAddress(address=f"{i} {postcode} Street", postcode=Postcode(postcode))
for i in range(n)
]
)

44
tests/domain/addresses/test_raw_address.py → tests/domain/addresses/test_unsanitised_address.py
View file

@ -2,36 +2,36 @@ import dataclasses
import pytest
from domain.addresses.raw_address import RawAddress
from domain.addresses.unsanitised_address import UnsanitisedAddress
from domain.postcode import Postcode
def test_raw_address_holds_postcode_value_object() -> None:
def test_unsanitised_address_holds_postcode_value_object() -> None:
# act
addr = RawAddress(address="1 The Street", postcode=Postcode("sw1a 1aa"))
addr = UnsanitisedAddress(address="1 The Street", postcode=Postcode("sw1a 1aa"))
# assert
assert addr.postcode == Postcode("SW1A1AA")
def test_raw_address_preserves_raw_address_verbatim() -> None:
# The free-text raw_address string is intentionally NOT normalised --
def test_unsanitised_address_preserves_unsanitised_address_verbatim() -> None:
# The free-text unsanitised_address string is intentionally NOT normalised --
# only the postcode is canonicalised, and that happens inside Postcode.
# act
addr = RawAddress(address=" 1 The Street ", postcode=Postcode("SW1A1AA"))
addr = UnsanitisedAddress(address=" 1 The Street ", postcode=Postcode("SW1A1AA"))
# assert
assert addr.address == " 1 The Street "
def test_raw_address_internal_reference_defaults_to_none() -> None:
def test_unsanitised_address_internal_reference_defaults_to_none() -> None:
# act
addr = RawAddress(address="1 The Street", postcode=Postcode("SW1A1AA"))
addr = UnsanitisedAddress(address="1 The Street", postcode=Postcode("SW1A1AA"))
# assert
assert addr.org_reference is None
def test_raw_address_internal_reference_accepted() -> None:
def test_unsanitised_address_internal_reference_accepted() -> None:
# act
addr = RawAddress(
addr = UnsanitisedAddress(
address="1 The Street",
postcode=Postcode("SW1A1AA"),
org_reference="cust-42",
@ -40,36 +40,36 @@ def test_raw_address_internal_reference_accepted() -> None:
assert addr.org_reference == "cust-42"
def test_raw_address_is_frozen() -> None:
def test_unsanitised_address_is_frozen() -> None:
# arrange
addr = RawAddress(address="1 The Street", postcode=Postcode("SW1A1AA"))
addr = UnsanitisedAddress(address="1 The Street", postcode=Postcode("SW1A1AA"))
# act / assert
with pytest.raises(dataclasses.FrozenInstanceError):
addr.postcode = Postcode("OTHER") # type: ignore[misc]
def test_raw_address_equality_uses_canonical_postcode() -> None:
def test_unsanitised_address_equality_uses_canonical_postcode() -> None:
# Postcode sanitises eagerly, so addresses built from different surface
# forms of the same postcode compare equal.
# arrange
a = RawAddress(address="1 The Street", postcode=Postcode("sw1a 1aa"))
b = RawAddress(address="1 The Street", postcode=Postcode("SW1A1AA"))
a = UnsanitisedAddress(address="1 The Street", postcode=Postcode("sw1a 1aa"))
b = UnsanitisedAddress(address="1 The Street", postcode=Postcode("SW1A1AA"))
# act / assert
assert a == b
def test_raw_address_source_row_defaults_to_empty_dict() -> None:
def test_unsanitised_address_source_row_defaults_to_empty_dict() -> None:
# act
addr = RawAddress(address="1 The Street", postcode=Postcode("SW1A1AA"))
addr = UnsanitisedAddress(address="1 The Street", postcode=Postcode("SW1A1AA"))
# assert
assert addr.additional_info == {}
def test_raw_address_carries_source_row() -> None:
def test_unsanitised_address_carries_source_row() -> None:
# arrange
row = {"Address 1": "1 The Street", "postcode": "SW1A 1AA", "SAP Score": "72"}
# act
addr = RawAddress(
addr = UnsanitisedAddress(
address="1 The Street",
postcode=Postcode("SW1A 1AA"),
additional_info=row,
@ -78,16 +78,16 @@ def test_raw_address_carries_source_row() -> None:
assert addr.additional_info == row
def test_raw_address_equality_ignores_source_row() -> None:
def test_unsanitised_address_equality_ignores_source_row() -> None:
# source_row is excluded from equality (and hashing): identity stays
# defined by the parsed fields.
# arrange
a = RawAddress(
a = UnsanitisedAddress(
address="1 The Street",
postcode=Postcode("SW1A1AA"),
additional_info={"x": "1"},
)
b = RawAddress(
b = UnsanitisedAddress(
address="1 The Street",
postcode=Postcode("SW1A1AA"),
additional_info={"y": "2"},

34
tests/orchestration/test_landlord_description_overrides_orchestrator.py
View file

@ -1,16 +1,16 @@
from __future__ import annotations
from domain.addresses.raw_address import AddressList, RawAddress
from domain.addresses.unsanitised_address import AddressList, UnsanitisedAddress
from domain.postcode import Postcode
from orchestration.sal_orchestrator import (
SALOrchestrator,
)
from repositories.raw_address.raw_address_list_repository import (
RawAddressListRepository,
from repositories.unsanitised_address.unsanitised_address_list_repository import (
UnsanitisedAddressListRepository,
)
class _StubRawAddressRepository(RawAddressListRepository):
class _StubUnsanitisedAddressRepository(UnsanitisedAddressListRepository):
"""``get_col_to_description_mappings`` never touches the repo."""
def load_batch(self, s3_uri: str) -> AddressList:
@ -20,8 +20,8 @@ class _StubRawAddressRepository(RawAddressListRepository):
raise NotImplementedError()
def _make_raw_address(landlord_additional_info: dict[str, str]) -> RawAddress:
return RawAddress(
def _make_unsanitised_address(landlord_additional_info: dict[str, str]) -> UnsanitisedAddress:
return UnsanitisedAddress(
address="1 High St",
postcode=Postcode("AA1 1AA"),
additional_info=landlord_additional_info,
@ -29,16 +29,16 @@ def _make_raw_address(landlord_additional_info: dict[str, str]) -> RawAddress:
def _orchestrator() -> SALOrchestrator:
return SALOrchestrator(raw_address_repo=_StubRawAddressRepository())
return SALOrchestrator(unsanitised_address_repo=_StubUnsanitisedAddressRepository())
def test_collects_every_value_per_shared_key() -> None:
# arrange: every address carries the same keys, all values distinct.
addresses = AddressList(
[
_make_raw_address({"description": "cosy", "condition": "new"}),
_make_raw_address({"description": "spacious", "condition": "worn"}),
_make_raw_address({"description": "bright", "condition": "fair"}),
_make_unsanitised_address({"description": "cosy", "condition": "new"}),
_make_unsanitised_address({"description": "spacious", "condition": "worn"}),
_make_unsanitised_address({"description": "bright", "condition": "fair"}),
]
)
@ -56,9 +56,9 @@ def test_repeated_values_collapse_to_one_variant() -> None:
# arrange: two addresses share the same wall description.
addresses = AddressList(
[
_make_raw_address({"description": "cosy"}),
_make_raw_address({"description": "cosy"}),
_make_raw_address({"description": "bright"}),
_make_unsanitised_address({"description": "cosy"}),
_make_unsanitised_address({"description": "cosy"}),
_make_unsanitised_address({"description": "bright"}),
]
)
@ -73,9 +73,9 @@ def test_case_only_variants_collapse_to_one() -> None:
# arrange: the same description typed with inconsistent casing.
addresses = AddressList(
[
_make_raw_address({"description": "Cosy"}),
_make_raw_address({"description": "cosy"}),
_make_raw_address({"description": "COSY"}),
_make_unsanitised_address({"description": "Cosy"}),
_make_unsanitised_address({"description": "cosy"}),
_make_unsanitised_address({"description": "COSY"}),
]
)
@ -96,7 +96,7 @@ def test_empty_address_list_yields_empty_mapping() -> None:
def test_single_address_yields_single_value_per_key() -> None:
# arrange
addresses = AddressList([_make_raw_address({"description": "cosy"})])
addresses = AddressList([_make_unsanitised_address({"description": "cosy"})])
# act
mappings = _orchestrator().get_col_to_description_mappings(addresses)

10
tests/orchestration/test_postcode_splitter_orchestrator.py
View file

@ -18,8 +18,8 @@ from orchestration.postcode_splitter_orchestrator import PostcodeSplitterOrchest
from orchestration.task_orchestrator import TaskOrchestrator
from repositories.tasks.subtask_postgres_repository import SubTaskPostgresRepository
from repositories.tasks.task_postgres_repository import TaskPostgresRepository
from repositories.raw_address.raw_address_list_csv_s3_repository import (
RawAddressListCsvS3Repository,
from repositories.unsanitised_address.unsanitised_address_list_csv_s3_repository import (
UnsanitisedAddressListCsvS3Repository,
)
BUCKET = "splitter-bucket"
@ -64,7 +64,7 @@ class Harness:
csv_client: CsvS3Client
boto_sqs: Any
queue_url: str
repo: RawAddressListCsvS3Repository
repo: UnsanitisedAddressListCsvS3Repository
@pytest.fixture
@ -78,7 +78,7 @@ def harness(db_engine: Engine) -> Iterator[Harness]:
queue_url = cast(str, queue["QueueUrl"])
csv_client = CsvS3Client(boto_s3, BUCKET)
repo = RawAddressListCsvS3Repository(csv_client, BUCKET)
repo = UnsanitisedAddressListCsvS3Repository(csv_client, BUCKET)
queue_client = Address2UprnQueueClient(boto_sqs, queue_url)
# DB: ephemeral PostgreSQL TaskOrchestrator
@ -91,7 +91,7 @@ def harness(db_engine: Engine) -> Iterator[Harness]:
splitter = PostcodeSplitterOrchestrator(
task_orchestrator=task_orchestrator,
raw_address_repo=repo,
unsanitised_address_repo=repo,
queue_client=queue_client,
max_batch_size=3,
)

0
tests/repositories/raw_address/__init__.py → tests/repositories/unsanitised_address/__init__.py
View file

0
tests/repositories/raw_address/conftest.py → tests/repositories/unsanitised_address/conftest.py
View file

36
tests/repositories/raw_address/test_raw_address_list_csv_s3_repository.py → tests/repositories/unsanitised_address/test_unsanitised_address_list_csv_s3_repository.py
View file

@ -3,11 +3,11 @@ from collections.abc import Iterator
import pytest
from moto import mock_aws
from domain.addresses.raw_address import AddressList, RawAddress
from domain.addresses.unsanitised_address import AddressList, UnsanitisedAddress
from domain.postcode import Postcode
from infrastructure.csv_s3_client import CsvS3Client
from repositories.raw_address.raw_address_list_csv_s3_repository import (
RawAddressListCsvS3Repository,
from repositories.unsanitised_address.unsanitised_address_list_csv_s3_repository import (
UnsanitisedAddressListCsvS3Repository,
)
from tests.infrastructure import make_boto_client
@ -15,22 +15,22 @@ BUCKET = "user-address-bucket"
@pytest.fixture
def repo() -> Iterator[RawAddressListCsvS3Repository]:
def repo() -> Iterator[UnsanitisedAddressListCsvS3Repository]:
with mock_aws():
boto_client = make_boto_client("s3")
boto_client.create_bucket(Bucket=BUCKET)
csv_client = CsvS3Client(boto_client, BUCKET)
yield RawAddressListCsvS3Repository(csv_client, BUCKET)
yield UnsanitisedAddressListCsvS3Repository(csv_client, BUCKET)
def _upload_csv(
repo: RawAddressListCsvS3Repository, rows: list[dict[str, str]], key: str
repo: UnsanitisedAddressListCsvS3Repository, rows: list[dict[str, str]], key: str
) -> str:
return repo._csv_client.save_rows(rows, key) # pyright: ignore[reportPrivateUsage]
def test_load_batch_parses_address_postcode_and_reference(
repo: RawAddressListCsvS3Repository,
repo: UnsanitisedAddressListCsvS3Repository,
) -> None:
# arrange
rows = [
@ -56,7 +56,7 @@ def test_load_batch_parses_address_postcode_and_reference(
def test_load_batch_uses_only_address_1_when_others_missing(
repo: RawAddressListCsvS3Repository,
repo: UnsanitisedAddressListCsvS3Repository,
) -> None:
# arrange
rows = [
@ -81,7 +81,7 @@ def test_load_batch_uses_only_address_1_when_others_missing(
def test_load_batch_handles_missing_internal_reference(
repo: RawAddressListCsvS3Repository,
repo: UnsanitisedAddressListCsvS3Repository,
) -> None:
# arrange
rows = [
@ -106,10 +106,10 @@ def test_load_batch_handles_missing_internal_reference(
def test_load_batch_captures_full_source_row(
repo: RawAddressListCsvS3Repository,
repo: UnsanitisedAddressListCsvS3Repository,
) -> None:
# A raw EPC-export-shaped row: the splitter must preserve every column,
# not just the ones it parses into RawAddress fields.
# not just the ones it parses into UnsanitisedAddress fields.
# arrange
row = {
"Asset Reference": "511",
@ -128,7 +128,7 @@ def test_load_batch_captures_full_source_row(
def test_load_batch_raises_when_postcode_column_absent(
repo: RawAddressListCsvS3Repository,
repo: UnsanitisedAddressListCsvS3Repository,
) -> None:
# arrange
rows = [{"Address 1": "1 High Street", "Property Type": "Flat"}]
@ -140,7 +140,7 @@ def test_load_batch_raises_when_postcode_column_absent(
def test_save_batch_passes_through_all_columns_and_appends_postcode_clean(
repo: RawAddressListCsvS3Repository,
repo: UnsanitisedAddressListCsvS3Repository,
) -> None:
# arrange
row = {
@ -169,12 +169,12 @@ def test_save_batch_passes_through_all_columns_and_appends_postcode_clean(
def test_save_batch_returns_uri_under_path_prefix(
repo: RawAddressListCsvS3Repository,
repo: UnsanitisedAddressListCsvS3Repository,
) -> None:
# arrange
addresses = AddressList(
[
RawAddress(
UnsanitisedAddress(
address="1 High Street",
postcode=Postcode("SW1A 1AA"),
additional_info={
@ -194,7 +194,7 @@ def test_save_batch_returns_uri_under_path_prefix(
def test_save_then_reload_round_trip_preserves_columns(
repo: RawAddressListCsvS3Repository,
repo: UnsanitisedAddressListCsvS3Repository,
) -> None:
# arrange
rows = [
@ -227,12 +227,12 @@ def test_save_then_reload_round_trip_preserves_columns(
def test_save_batch_uses_unique_filename_per_call(
repo: RawAddressListCsvS3Repository,
repo: UnsanitisedAddressListCsvS3Repository,
) -> None:
# arrange
addresses = AddressList(
[
RawAddress(
UnsanitisedAddress(
address="1 High Street",
postcode=Postcode("SW1A 1AA"),
additional_info={