def test_post_deposit_multipart_without_origin_url(
authenticated_client,
deposit_collection,
atom_dataset,
mocker,
deposit_user,
sample_archive,
):
# given
url = reverse(COL_IRI, args=[deposit_collection.name])
data_atom_entry = atom_dataset["entry-data-deposit-binary"]
id_ = str(uuid.uuid4())
mocker.patch("uuid.uuid4", return_value=id_)
# when
response = post_multipart(
authenticated_client,
url,
sample_archive,
data_atom_entry,
HTTP_IN_PROGRESS="false",
)
assert response.status_code == status.HTTP_201_CREATED
response_content = parse_xml(response.content)
deposit_id = int(
response_content.findtext("swh:deposit_id", namespaces=NAMESPACES))
deposit = Deposit.objects.get(pk=deposit_id)
assert deposit.collection == deposit_collection
assert deposit.origin_url == deposit_user.provider_url + id_
assert deposit.status == DEPOSIT_STATUS_DEPOSITED
def test_post_deposit_multipart_if_upload_size_limit_exceeded(
authenticated_client, deposit_collection, atom_dataset,
sample_archive):
# given
url = reverse(COL_IRI, args=[deposit_collection.name])
archive = {
**sample_archive,
"data": sample_archive["data"] * 100,
}
data_atom_entry = atom_dataset["entry-data-deposit-binary"]
external_id = "external-id"
# when
response = post_multipart(
authenticated_client,
url,
archive,
data_atom_entry,
HTTP_IN_PROGRESS="false",
HTTP_SLUG=external_id,
)
# then
assert response.status_code == status.HTTP_413_REQUEST_ENTITY_TOO_LARGE
assert b"Upload size limit exceeded" in response.content
with pytest.raises(Deposit.DoesNotExist):
Deposit.objects.get(external_id=external_id)
def test_post_deposit_multipart(
authenticated_client,
deposit_collection,
atom_dataset,
mocker,
deposit_user,
sample_archive,
):
# given
external_id = "foobar"
origin_url = deposit_user.provider_url + external_id
url = reverse(COL_IRI, args=[deposit_collection.name])
data_atom_entry = atom_dataset["entry-data0"] % origin_url
# when
response = post_multipart(
authenticated_client,
url,
sample_archive,
data_atom_entry,
HTTP_IN_PROGRESS="false",
)
assert response.status_code == status.HTTP_201_CREATED
response_content = parse_xml(response.content)
deposit_id = int(
response_content.findtext("swh:deposit_id", namespaces=NAMESPACES))
deposit = Deposit.objects.get(pk=deposit_id)
assert deposit.collection == deposit_collection
assert deposit.origin_url == origin_url
assert deposit.status == DEPOSIT_STATUS_DEPOSITED
def test_add_both_archive_and_metadata_to_deposit(
authenticated_client,
deposit_collection,
partial_deposit_with_metadata,
atom_dataset,
sample_archive,
deposit_user,
):
"""Scenario: Add both a new archive and new metadata to a partial deposit is ok
Response: 201
"""
deposit = partial_deposit_with_metadata
origin_url = deposit_user.provider_url + deposit.external_id
requests = DepositRequest.objects.filter(deposit=deposit, type="metadata")
assert len(requests) == 1
requests_archive0 = DepositRequest.objects.filter(deposit=deposit,
type="archive")
assert len(requests_archive0) == 1
data_atom_entry = atom_dataset["entry-data1"]
response = post_multipart(
authenticated_client,
reverse(SE_IRI, args=[deposit_collection.name, deposit.id]),
sample_archive,
data_atom_entry,
)
assert response.status_code == status.HTTP_201_CREATED
requests = DepositRequest.objects.filter(deposit=deposit,
type="metadata").order_by("id")
assert len(requests) == 1 + 1, "New deposit request archive got added"
expected_raw_meta0 = atom_dataset["entry-data0"] % origin_url
# a new one was added
assert requests[0].raw_metadata == expected_raw_meta0
assert requests[1].raw_metadata == data_atom_entry
# check we did not touch the other parts
requests_archive1 = DepositRequest.objects.filter(deposit=deposit,
type="archive")
assert len(
requests_archive1) == 1 + 1, "New deposit request metadata got added"
def test_post_deposit_multipart_zip(authenticated_client, deposit_collection,
atom_dataset, sample_archive):
"""one multipart deposit (zip+xml) should be accepted"""
# given
url = reverse(COL_IRI, args=[deposit_collection.name])
data_atom_entry = atom_dataset["entry-data-deposit-binary"]
external_id = "external-id"
# when
response = post_multipart(
authenticated_client,
url,
sample_archive,
data_atom_entry,
HTTP_IN_PROGRESS="false",
HTTP_SLUG=external_id,
)
# then
assert response.status_code == status.HTTP_201_CREATED
response_content = parse_xml(response.content)
deposit_id = int(
response_content.findtext("swh:deposit_id", namespaces=NAMESPACES))
deposit = Deposit.objects.get(pk=deposit_id)
assert deposit.status == DEPOSIT_STATUS_DEPOSITED
assert deposit.external_id == external_id
assert deposit.collection == deposit_collection
assert deposit.swhid is None
deposit_requests = DepositRequest.objects.filter(deposit=deposit)
assert len(deposit_requests) == 2
for deposit_request in deposit_requests:
assert deposit_request.deposit == deposit
if deposit_request.type == "archive":
check_archive(sample_archive["name"], deposit_request.archive.name)
assert deposit_request.raw_metadata is None
else:
assert (parse_xml(deposit_request.raw_metadata).findtext(
"atom:id", namespaces=NAMESPACES) ==
"urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a")
assert deposit_request.raw_metadata == data_atom_entry
def test_post_deposit_multipart_400_when_badly_formatted_xml(
authenticated_client, deposit_collection, sample_archive,
atom_dataset):
# given
url = reverse(COL_IRI, args=[deposit_collection.name])
data_atom_entry_ko = atom_dataset["entry-data-ko"]
# when
response = post_multipart(
authenticated_client,
url,
sample_archive,
data_atom_entry_ko,
HTTP_IN_PROGRESS="false",
HTTP_SLUG="external-id",
)
assert b"Malformed xml metadata" in response.content
assert response.status_code == status.HTTP_400_BAD_REQUEST
def test_post_deposit_multipart_put_to_replace_metadata(
authenticated_client, deposit_collection, atom_dataset,
sample_archive):
"""One multipart deposit followed by a metadata update should be
accepted
"""
# given
url = reverse(COL_IRI, args=[deposit_collection.name])
data_atom_entry = atom_dataset["entry-data-deposit-binary"]
external_id = "external-id"
# when
response = post_multipart(
authenticated_client,
url,
sample_archive,
data_atom_entry,
HTTP_IN_PROGRESS="true",
HTTP_SLUG=external_id,
)
# then
assert response.status_code == status.HTTP_201_CREATED
response_content = parse_xml(response.content)
deposit_id = int(
response_content.findtext("swh:deposit_id", namespaces=NAMESPACES))
deposit = Deposit.objects.get(pk=deposit_id)
assert deposit.status == "partial"
assert deposit.external_id == external_id
assert deposit.collection == deposit_collection
assert deposit.swhid is None
deposit_requests = DepositRequest.objects.filter(deposit=deposit)
assert len(deposit_requests) == 2
for deposit_request in deposit_requests:
assert deposit_request.deposit == deposit
if deposit_request.type == "archive":
check_archive(sample_archive["name"], deposit_request.archive.name)
else:
assert (parse_xml(deposit_request.raw_metadata).findtext(
"atom:id", namespaces=NAMESPACES) ==
"urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a")
assert deposit_request.raw_metadata == data_atom_entry
replace_metadata_uri = response["location"]
response = authenticated_client.put(
replace_metadata_uri,
content_type="application/atom+xml;type=entry",
data=atom_dataset["entry-data-deposit-binary"],
HTTP_IN_PROGRESS="false",
)
assert response.status_code == status.HTTP_204_NO_CONTENT
# deposit_id did not change
deposit = Deposit.objects.get(pk=deposit_id)
assert deposit.status == DEPOSIT_STATUS_DEPOSITED
assert deposit.external_id == external_id
assert deposit.collection == deposit_collection
assert deposit.swhid is None
deposit_requests = DepositRequest.objects.filter(deposit=deposit)
assert len(deposit_requests) == 2
for deposit_request in deposit_requests:
assert deposit_request.deposit == deposit
if deposit_request.type == "archive":
check_archive(sample_archive["name"], deposit_request.archive.name)
else:
assert (parse_xml(deposit_request.raw_metadata).findtext(
"atom:id", namespaces=NAMESPACES) ==
"urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a")
assert (deposit_request.raw_metadata ==
atom_dataset["entry-data-deposit-binary"])