2020-07-17 16:59:25 -06:00
|
|
|
from github import UnknownObjectException
|
2022-01-06 11:46:54 -05:00
|
|
|
from sqlalchemy import desc, column
|
2022-02-02 12:59:56 -05:00
|
|
|
|
2020-05-23 15:08:17 -04:00
|
|
|
from tests.base_test import BaseTest
|
2020-07-17 16:59:25 -06:00
|
|
|
from unittest.mock import patch, Mock
|
2020-06-04 09:49:42 -04:00
|
|
|
|
2022-01-06 11:46:54 -05:00
|
|
|
from crc import db, session
|
|
|
|
from crc.api.common import ApiError
|
|
|
|
from crc.models.file import FileModel, FileDataModel, CONTENT_TYPES
|
2022-02-07 15:17:32 -05:00
|
|
|
from crc.models.workflow import WorkflowModel
|
2020-05-23 15:08:17 -04:00
|
|
|
from crc.services.workflow_processor import WorkflowProcessor
|
2022-02-02 12:59:56 -05:00
|
|
|
from crc.services.user_file_service import UserFileService
|
2020-05-23 15:08:17 -04:00
|
|
|
|
2020-07-17 16:59:25 -06:00
|
|
|
|
|
|
|
class FakeGithubCreates(Mock):
|
|
|
|
def get_user(var):
|
|
|
|
class FakeUser(Mock):
|
|
|
|
def get_repo(var, name):
|
|
|
|
class FakeRepo(Mock):
|
2020-08-14 11:04:22 -06:00
|
|
|
def get_contents(var, filename, ref):
|
2021-05-04 13:39:49 -04:00
|
|
|
raise UnknownObjectException(status='Failure', data='Failed data', headers=[])
|
2020-08-14 11:04:22 -06:00
|
|
|
def update_file(var, path, message, content, sha, branch):
|
2020-07-17 16:59:25 -06:00
|
|
|
pass
|
|
|
|
return FakeRepo()
|
|
|
|
return FakeUser()
|
|
|
|
|
|
|
|
|
|
|
|
class FakeGithub(Mock):
|
|
|
|
def get_user(var):
|
|
|
|
class FakeUser(Mock):
|
|
|
|
def get_repo(var, name):
|
|
|
|
class FakeRepo(Mock):
|
2020-08-14 11:04:22 -06:00
|
|
|
def get_contents(var, filename, ref):
|
2020-07-17 16:59:25 -06:00
|
|
|
fake_file = Mock()
|
|
|
|
fake_file.decoded_content = b'Some bytes'
|
|
|
|
fake_file.path = '/el/path/'
|
|
|
|
fake_file.data = 'Serious data'
|
|
|
|
fake_file.sha = 'Sha'
|
|
|
|
return fake_file
|
2020-08-14 11:04:22 -06:00
|
|
|
def get_branches(var):
|
|
|
|
branch1 = Mock()
|
|
|
|
branch1.name = 'branch1'
|
|
|
|
branch2 = Mock()
|
|
|
|
branch2.name = 'branch2'
|
|
|
|
master = Mock()
|
|
|
|
master.name = 'master'
|
|
|
|
return [branch1, branch2, master]
|
|
|
|
def update_file(var, path, message, content, sha, branch):
|
2020-07-17 16:59:25 -06:00
|
|
|
pass
|
|
|
|
return FakeRepo()
|
|
|
|
return FakeUser()
|
|
|
|
|
|
|
|
|
2020-05-23 15:08:17 -04:00
|
|
|
class TestFileService(BaseTest):
|
|
|
|
"""Largely tested via the test_file_api, and time is tight, but adding new tests here."""
|
|
|
|
|
|
|
|
def test_add_file_from_task_increments_version_and_replaces_on_subsequent_add(self):
|
|
|
|
workflow = self.create_workflow('file_upload_form')
|
|
|
|
processor = WorkflowProcessor(workflow)
|
|
|
|
task = processor.next_task()
|
|
|
|
irb_code = "UVACompl_PRCAppr" # The first file referenced in pb required docs.
|
2022-02-02 12:59:56 -05:00
|
|
|
UserFileService.add_workflow_file(workflow_id=workflow.id,
|
|
|
|
task_spec_name=task.get_name(),
|
|
|
|
name="anything.png", content_type="text",
|
|
|
|
binary_data=b'1234', irb_doc_code=irb_code)
|
2020-05-23 15:08:17 -04:00
|
|
|
# Add the file again with different data
|
2022-02-02 12:59:56 -05:00
|
|
|
UserFileService.add_workflow_file(workflow_id=workflow.id,
|
|
|
|
task_spec_name=task.get_name(),
|
|
|
|
name="anything.png", content_type="text",
|
|
|
|
binary_data=b'5678', irb_doc_code=irb_code)
|
2020-05-23 15:08:17 -04:00
|
|
|
|
2022-02-02 12:59:56 -05:00
|
|
|
file_models = UserFileService.get_workflow_files(workflow_id=workflow.id)
|
2020-06-05 12:08:46 -06:00
|
|
|
self.assertEqual(1, len(file_models))
|
2020-05-28 20:03:50 -04:00
|
|
|
|
2022-02-02 12:59:56 -05:00
|
|
|
file_data = UserFileService.get_workflow_data_files(workflow_id=workflow.id)
|
2020-06-05 12:08:46 -06:00
|
|
|
self.assertEqual(1, len(file_data))
|
|
|
|
self.assertEqual(2, file_data[0].version)
|
2021-08-16 10:18:29 -04:00
|
|
|
self.assertEqual(4, file_data[0].size) # File dat size is included.
|
2020-05-23 15:08:17 -04:00
|
|
|
|
|
|
|
def test_add_file_from_form_increments_version_and_replaces_on_subsequent_add_with_same_name(self):
|
|
|
|
workflow = self.create_workflow('file_upload_form')
|
|
|
|
processor = WorkflowProcessor(workflow)
|
|
|
|
task = processor.next_task()
|
|
|
|
irb_code = "UVACompl_PRCAppr" # The first file referenced in pb required docs.
|
2022-02-02 12:59:56 -05:00
|
|
|
UserFileService.add_workflow_file(workflow_id=workflow.id,
|
2020-06-04 09:49:42 -04:00
|
|
|
irb_doc_code=irb_code,
|
2021-08-26 10:43:28 -04:00
|
|
|
task_spec_name=task.get_name(),
|
2020-06-04 09:49:42 -04:00
|
|
|
name="anything.png", content_type="text",
|
|
|
|
binary_data=b'1234')
|
|
|
|
# Add the file again with different data
|
2022-02-02 12:59:56 -05:00
|
|
|
UserFileService.add_workflow_file(workflow_id=workflow.id,
|
2020-06-04 09:49:42 -04:00
|
|
|
irb_doc_code=irb_code,
|
2021-08-26 10:43:28 -04:00
|
|
|
task_spec_name=task.get_name(),
|
2020-06-04 09:49:42 -04:00
|
|
|
name="anything.png", content_type="text",
|
|
|
|
binary_data=b'5678')
|
|
|
|
|
2020-05-23 15:08:17 -04:00
|
|
|
def test_add_file_from_form_allows_multiple_files_with_different_names(self):
|
|
|
|
workflow = self.create_workflow('file_upload_form')
|
|
|
|
processor = WorkflowProcessor(workflow)
|
|
|
|
task = processor.next_task()
|
|
|
|
irb_code = "UVACompl_PRCAppr" # The first file referenced in pb required docs.
|
2022-02-02 12:59:56 -05:00
|
|
|
UserFileService.add_workflow_file(workflow_id=workflow.id,
|
A major refactor of how we search and store files, as there was a lot of confusing bits in here.
From an API point of view you can do the following (and only the following)
/files?workflow_spec_id=x
* You can find all files associated with a workflow_spec_id, and add a file with a workflow_spec_id
/files?workflow_id=x
* You can find all files associated with a workflow_id, and add a file that is directly associated with the workflow
/files?workflow_id=x&form_field_key=y
* You can find all files associated with a form element on a running workflow, and add a new file.
Note: you can add multiple files to the same form_field_key, IF they have different file names. If the same name, the original file is archived,
and the new file takes its place.
The study endpoints always return a list of the file metadata associated with the study. Removed /studies-files, but there is an
endpoint called
/studies/all - that returns all the studies in the system, and does include their files.
On a deeper level:
The File model no longer contains:
- study_id,
- task_id,
- form_field_key
Instead, if the file is associated with workflow - then that is the one way it is connected to the study, and we use this relationship to find files for a study.
A file is never associated with a task_id, as these change when the workflow is reloaded.
The form_field_key must match the irb_doc_code, so when requesting files for a form field, we just look up the irb_doc_code.
2020-05-28 08:27:26 -04:00
|
|
|
irb_doc_code=irb_code,
|
2021-08-26 10:43:28 -04:00
|
|
|
task_spec_name=task.get_name(),
|
A major refactor of how we search and store files, as there was a lot of confusing bits in here.
From an API point of view you can do the following (and only the following)
/files?workflow_spec_id=x
* You can find all files associated with a workflow_spec_id, and add a file with a workflow_spec_id
/files?workflow_id=x
* You can find all files associated with a workflow_id, and add a file that is directly associated with the workflow
/files?workflow_id=x&form_field_key=y
* You can find all files associated with a form element on a running workflow, and add a new file.
Note: you can add multiple files to the same form_field_key, IF they have different file names. If the same name, the original file is archived,
and the new file takes its place.
The study endpoints always return a list of the file metadata associated with the study. Removed /studies-files, but there is an
endpoint called
/studies/all - that returns all the studies in the system, and does include their files.
On a deeper level:
The File model no longer contains:
- study_id,
- task_id,
- form_field_key
Instead, if the file is associated with workflow - then that is the one way it is connected to the study, and we use this relationship to find files for a study.
A file is never associated with a task_id, as these change when the workflow is reloaded.
The form_field_key must match the irb_doc_code, so when requesting files for a form field, we just look up the irb_doc_code.
2020-05-28 08:27:26 -04:00
|
|
|
name="anything.png", content_type="text",
|
|
|
|
binary_data=b'1234')
|
2020-05-23 15:08:17 -04:00
|
|
|
# Add the file again with different data
|
2022-02-02 12:59:56 -05:00
|
|
|
UserFileService.add_workflow_file(workflow_id=workflow.id,
|
A major refactor of how we search and store files, as there was a lot of confusing bits in here.
From an API point of view you can do the following (and only the following)
/files?workflow_spec_id=x
* You can find all files associated with a workflow_spec_id, and add a file with a workflow_spec_id
/files?workflow_id=x
* You can find all files associated with a workflow_id, and add a file that is directly associated with the workflow
/files?workflow_id=x&form_field_key=y
* You can find all files associated with a form element on a running workflow, and add a new file.
Note: you can add multiple files to the same form_field_key, IF they have different file names. If the same name, the original file is archived,
and the new file takes its place.
The study endpoints always return a list of the file metadata associated with the study. Removed /studies-files, but there is an
endpoint called
/studies/all - that returns all the studies in the system, and does include their files.
On a deeper level:
The File model no longer contains:
- study_id,
- task_id,
- form_field_key
Instead, if the file is associated with workflow - then that is the one way it is connected to the study, and we use this relationship to find files for a study.
A file is never associated with a task_id, as these change when the workflow is reloaded.
The form_field_key must match the irb_doc_code, so when requesting files for a form field, we just look up the irb_doc_code.
2020-05-28 08:27:26 -04:00
|
|
|
irb_doc_code=irb_code,
|
2021-08-26 10:43:28 -04:00
|
|
|
task_spec_name=task.get_name(),
|
A major refactor of how we search and store files, as there was a lot of confusing bits in here.
From an API point of view you can do the following (and only the following)
/files?workflow_spec_id=x
* You can find all files associated with a workflow_spec_id, and add a file with a workflow_spec_id
/files?workflow_id=x
* You can find all files associated with a workflow_id, and add a file that is directly associated with the workflow
/files?workflow_id=x&form_field_key=y
* You can find all files associated with a form element on a running workflow, and add a new file.
Note: you can add multiple files to the same form_field_key, IF they have different file names. If the same name, the original file is archived,
and the new file takes its place.
The study endpoints always return a list of the file metadata associated with the study. Removed /studies-files, but there is an
endpoint called
/studies/all - that returns all the studies in the system, and does include their files.
On a deeper level:
The File model no longer contains:
- study_id,
- task_id,
- form_field_key
Instead, if the file is associated with workflow - then that is the one way it is connected to the study, and we use this relationship to find files for a study.
A file is never associated with a task_id, as these change when the workflow is reloaded.
The form_field_key must match the irb_doc_code, so when requesting files for a form field, we just look up the irb_doc_code.
2020-05-28 08:27:26 -04:00
|
|
|
name="a_different_thing.png", content_type="text",
|
|
|
|
binary_data=b'5678')
|
2022-02-02 12:59:56 -05:00
|
|
|
file_models = UserFileService.get_workflow_files(workflow_id=workflow.id)
|
2020-06-05 12:08:46 -06:00
|
|
|
self.assertEqual(2, len(file_models))
|
2020-07-17 16:59:25 -06:00
|
|
|
|