def test_create_compressed_batch(cidc_api, clean_db, monkeypatch):
user_id = setup_user(cidc_api, monkeypatch)
file_id_1, file_id_2 = setup_downloadable_files(cidc_api)
with cidc_api.app_context():
url_1 = DownloadableFiles.find_by_id(file_id_1).object_url
url_2 = DownloadableFiles.find_by_id(file_id_2).object_url
client = cidc_api.test_client()
url = "/downloadable_files/compressed_batch"
# A JSON body containing a file ID list must be provided
res = client.post(url)
assert res.status_code == 422
# User has no permissions, so no files should be found
short_file_list = {"file_ids": [file_id_1, file_id_2]}
res = client.post(url, json=short_file_list)
assert res.status_code == 404
# Give the user one permission
with cidc_api.app_context():
perm = Permissions(
granted_to_user=user_id,
trial_id=trial_id_1,
upload_type=upload_types[0],
granted_by_user=user_id,
)
perm.insert()
# Mock GCS client
blob = MagicMock()
bucket = MagicMock()
bucket.blob.return_value = blob
monkeypatch.setattr(
"cidc_api.resources.downloadable_files.gcloud_client._get_bucket",
lambda _: bucket,
)
signed_url = "fake/signed/url"
monkeypatch.setattr(
"cidc_api.resources.downloadable_files.gcloud_client.get_signed_url",
lambda *_: signed_url,
)
# User has one permission, s0 the endpoint should try to create
# a compressed batch file with the single file the user has
# access to in it.
res = client.post(url, json=short_file_list)
assert res.status_code == 200
assert res.json == signed_url
print(bucket.get_blob.call_args_list)
bucket.get_blob.assert_called_with(url_1)
blob.upload_from_filename.assert_called_once()
bucket.reset_mock()
blob.reset_mock()
make_admin(user_id, cidc_api)
# Admin has access to both files, but together they are too large
res = client.post(url, json=short_file_list)
assert res.status_code == 400
assert "batch too large" in res.json["_error"]["message"]
bucket.get_blob.assert_not_called()
blob.upload_from_filename.assert_not_called()
# Decrease the size of one of the files and try again
with cidc_api.app_context():
df = DownloadableFiles.find_by_id(file_id_1)
df.file_size_bytes = 1
df.update()
res = client.post(url, json=short_file_list)
assert res.status_code == 200
assert res.json == signed_url
assert call(url_1) in bucket.get_blob.call_args_list
assert call(url_2) in bucket.get_blob.call_args_list
blob.upload_from_filename.assert_called_once()
def test_create_downloadable_file_from_blob(clean_db, monkeypatch):
"""Try to create a downloadable file from a GCS blob"""
fake_blob = MagicMock()
fake_blob.name = "name"
fake_blob.md5_hash = "12345"
fake_blob.crc32c = "54321"
fake_blob.size = 5
fake_blob.time_created = datetime.now()
clean_db.add(
TrialMetadata(
trial_id="id",
metadata_json={
"protocol_identifier": "id",
"allowed_collection_event_names": [],
"allowed_cohort_names": [],
"participants": [],
},
)
)
df = DownloadableFiles.create_from_blob(
"id", "pbmc", "Shipping Manifest", "pbmc/shipping", fake_blob
)
# Mock artifact upload publishing
publisher = MagicMock()
monkeypatch.setattr("cidc_api.models.models.publish_artifact_upload", publisher)
# Check that the file was created
assert 1 == clean_db.query(DownloadableFiles).count()
df_lookup = DownloadableFiles.find_by_id(df.id)
assert df_lookup.object_url == fake_blob.name
assert df_lookup.data_format == "Shipping Manifest"
assert df_lookup.file_size_bytes == fake_blob.size
assert df_lookup.md5_hash == fake_blob.md5_hash
assert df_lookup.crc32c_hash == fake_blob.crc32c
# uploading second time to check non duplicating entries
fake_blob.size = 6
fake_blob.md5_hash = "6"
df = DownloadableFiles.create_from_blob(
"id", "pbmc", "Shipping Manifest", "pbmc/shipping", fake_blob
)
# Check that the file was created
assert 1 == clean_db.query(DownloadableFiles).count()
df_lookup = DownloadableFiles.find_by_id(df.id)
assert df_lookup.file_size_bytes == 6
assert df_lookup.md5_hash == "6"
# Check that no artifact upload event was published
publisher.assert_not_called()
# Check that artifact upload publishes
DownloadableFiles.create_from_blob(
"id",
"pbmc",
"Shipping Manifest",
"pbmc/shipping",
fake_blob,
alert_artifact_upload=True,
)
publisher.assert_called_once_with(fake_blob.name)