Merge pull request #371 from sartography/zip-documents-379

Zip documents #379
This commit is contained in:
Mike Cullerton 2021-09-14 17:42:13 -04:00 committed by GitHub
commit 66bfbf0a49
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 115 additions and 2 deletions

View File

@ -0,0 +1,58 @@
from crc import session
from crc.api.common import ApiError
from crc.models.file import FileModel, FileDataModel
from crc.scripts.script import Script
from crc.services.file_service import FileService
from crc.services.study_service import StudyService
import os
import zipfile
class GetZippedFiles(Script):
"""This script creates a zip document from a list of file ids"""
def get_description(self):
"""Creates a zip file from a list of file_ids.
This is meant to use as an attachment to an email message"""
def do_task_validate_only(self, task, study_id, workflow_id, *args, **kwargs):
if 'file_ids' in kwargs.keys():
return True
return False
def do_task(self, task, study_id, workflow_id, *args, **kwargs):
if 'file_ids' in kwargs.keys():
doc_info = StudyService().get_documents_status(study_id)
if 'filename' in kwargs.keys():
zip_filename = kwargs['filename']
else:
zip_filename = 'attachments.zip'
file_ids = kwargs['file_ids']
files = session.query(FileModel).filter(FileModel.id.in_(file_ids)).all()
if files:
# Create a temporary zipfile with the requested files
with zipfile.ZipFile(zip_filename, mode='x', compression=zipfile.ZIP_DEFLATED) as zfw:
for file in files:
zip_key_words = doc_info[file.irb_doc_code]['zip_key_words']
file_name = f'{study_id} {zip_key_words} {file.name}'
file_data = session.query(FileDataModel).filter(FileDataModel.file_model_id == file.id).first()
zfw.writestr(file_name, file_data.data)
# Add the zipfile to the DB, and grab the file_model
with open(zip_filename, mode='rb') as handle:
file_model = FileService().add_workflow_file(workflow_id, None, task.name, zip_filename, 'application/zip', handle.read())
# Delete the temporary zipfile
os.remove(zip_filename)
# Return the file_model
return file_model
else:
raise ApiError(code='missing_file_ids',
message='You must include a list of file_ids.')

View File

@ -301,7 +301,7 @@ class TestFilesApi(BaseTest):
self.assert_success(rv) self.assert_success(rv)
json_data = json.loads(rv.get_data(as_text=True)) json_data = json.loads(rv.get_data(as_text=True))
self.assertEqual('Ancillary Document', json_data['document']['category1']) self.assertEqual('Ancillary Document', json_data['document']['category1'])
self.assertEqual('CRC', json_data['document']['Who Uploads?']) self.assertEqual('Study Team', json_data['document']['who_uploads?'])
def test_delete_file(self): def test_delete_file(self):
self.load_example_data() self.load_example_data()

View File

@ -0,0 +1,55 @@
from tests.base_test import BaseTest
from crc import session
from crc.models.file import FileModel, FileDataModel
from crc.models.workflow import WorkflowModel
from crc.models.study import StudyModel
from crc.scripts.get_zipped_files import GetZippedFiles
from crc.services.file_service import FileService
import io
import os
import zipfile
class TestGetZippedFiles(BaseTest):
def test_get_zipped_files(self):
self.load_example_data()
study = session.query(StudyModel).order_by(StudyModel.id.desc()).first()
workflow = session.query(WorkflowModel).first()
workflow_api = self.get_workflow_api(workflow)
task = workflow_api.next_task
# Add files to use in the test
FileService.add_workflow_file(workflow_id=workflow.id,
name="document_1.png", content_type="text",
task_spec_name=task.name,
binary_data=b'1234', irb_doc_code='Study_Protocol_Document')
FileService.add_workflow_file(workflow_id=workflow.id,
name="document_2.txt", content_type="text",
task_spec_name=task.name,
binary_data=b'1234', irb_doc_code='Study_App_Doc')
FileService.add_workflow_file(workflow_id=workflow.id,
name="document_3.pdf", content_type="text",
task_spec_name=task.name,
binary_data=b'1234', irb_doc_code='Admin_AdvChklst')
# Gather the file_ids
file_ids = []
files = session.query(FileModel).filter(FileModel.irb_doc_code != '').all()
for file in files:
file_ids.append(file.id)
# Send files to the zipper, receive file_model in return
file_model = GetZippedFiles().do_task(task, study.id, workflow.id, file_ids=file_ids, filename='another_attachment.zip')
file_data = session.query(FileDataModel).filter(FileDataModel.file_model_id == file_model.id).first()
# Test what we get back in the file_model
with zipfile.ZipFile(io.BytesIO(file_data.data), 'r') as zf:
self.assertIsInstance(zf, zipfile.ZipFile)
for name in zf.namelist():
info = zf.getinfo(name)
self.assertIn(os.path.basename(info.filename), ['1 Protocol document_1.png', '1 Application document_2.txt', '1 document_3.pdf'])
file = zf.read(name)
self.assertEqual(b'1234', file)

View File

@ -129,7 +129,7 @@ class TestStudyService(BaseTest):
self.assertEqual("UVA Compliance", documents["UVACompl_PRCAppr"]['category1']) self.assertEqual("UVA Compliance", documents["UVACompl_PRCAppr"]['category1'])
self.assertEqual("PRC Approval", documents["UVACompl_PRCAppr"]['category2']) self.assertEqual("PRC Approval", documents["UVACompl_PRCAppr"]['category2'])
self.assertEqual("", documents["UVACompl_PRCAppr"]['category3']) self.assertEqual("", documents["UVACompl_PRCAppr"]['category3'])
self.assertEqual("CRC", documents["UVACompl_PRCAppr"]['Who Uploads?']) self.assertEqual("Study Team", documents["UVACompl_PRCAppr"]['who_uploads?'])
self.assertEqual(0, documents["UVACompl_PRCAppr"]['count']) self.assertEqual(0, documents["UVACompl_PRCAppr"]['count'])
self.assertEqual(True, documents["UVACompl_PRCAppr"]['required']) self.assertEqual(True, documents["UVACompl_PRCAppr"]['required'])
self.assertEqual(6, documents["UVACompl_PRCAppr"]['id']) self.assertEqual(6, documents["UVACompl_PRCAppr"]['id'])