def testBadGroupTypeInCSV(self):
csv_string_bad = ("filename,title,document_type,url,organization\n"
"0bf5755e-3a08-4024-9d2f-0ea155a9bd17.pdf,NUTRA NAIL,9,, \n"
"0c68ab16-2065-4d9b-a8f2-e428eb192465.pdf,Body Cream,4,, \n")
# DocumentType.objects.all().exclude(group_type__title='Composition').values('id', 'title')
# assigning the (incompatible) *chemical use disclosure* document type in row 1 of the csv
data = io.StringIO(csv_string_bad)
csv_len = len(csv_string_bad)
sample_csv = InMemoryUploadedFile(data,
field_name='csv',
name='register_records.csv',
content_type='text/csv',
size=csv_len,
charset='utf-8')
form_data= {'name': ['Composition Type Group'],
'description': ['test data group'],
'group_type': ['2'], # Composition
'downloaded_by': ['1'],
'downloaded_at': ['08/02/2018'],
'download_script': ['1'],
'data_source': ['10']}
request = self.factory.post(path='/datagroup/new', data=form_data)
request.FILES['csv'] = sample_csv
request.user = User.objects.get(username='******')
request.session={}
request.session['datasource_title'] = 'Walmart'
request.session['datasource_pk'] = 10
resp = views.data_group_create(pk = 10 , request=request)
# the upload form should be invalid
self.assertIn('CSV has bad data in row/s:'.encode(), resp.content)
def test_datagroup_create_dupe_filename(self):
csv_string = (
"filename,title,document_type,url,organization\n"
"0bf5755e-3a08-4024-9d2f-0ea155a9bd17.pdf,NUTRA NAIL,1,, \n"
"0bf5755e-3a08-4024-9d2f-0ea155a9bd17.pdf,Body Cream,1,, \n")
data = io.StringIO(csv_string)
sample_csv = InMemoryUploadedFile(data,
field_name='csv',
name='register_records.csv',
content_type='text/csv',
size=len(csv_string),
charset='utf-8')
form_data = {
'name': ['Walmart MSDS Test Group'],
'description': ['test data group'],
'group_type': ['1'],
'downloaded_by': [str(User.objects.get(username='******').pk)],
'downloaded_at': ['08/02/2018'],
'download_script': ['1'],
'data_source': ['10']
}
request = self.factory.post(path='/datagroup/new/', data=form_data)
request.FILES['csv'] = sample_csv
request.user = User.objects.get(username='******')
request.session = {}
request.session['datasource_title'] = 'Walmart'
request.session['datasource_pk'] = 10
resp = views.data_group_create(request=request, pk=10)
self.assertContains(resp, 'Duplicate filename found')
def test_upload_html_as_datadoc(self):
csv_string = (
"filename,title,document_type,url,organization\n"
"alberto_balsam_conditioner_antioxidant_blueberry.html,Example Datadocument from HTML,ID,, \n"
)
data = io.StringIO(csv_string)
csv_len = len(csv_string)
sample_csv = InMemoryUploadedFile(
data,
field_name="csv",
name="register_records.csv",
content_type="text/csv",
size=csv_len,
charset="utf-8",
)
form_data = {
"name": ["California Pesticides"],
"description": ["test data group"],
"group_type": ["2"], # Composition
"downloaded_by": ["1"],
"downloaded_at": ["08/02/2018"],
"download_script": ["1"],
"data_source": ["10"],
}
request = self.factory.post(path="/datagroup/new", data=form_data)
request.FILES["csv"] = sample_csv
request.user = User.objects.get(username="******")
request.session = {}
request.session["datasource_title"] = "Walmart"
request.session["datasource_pk"] = 10
resp = views.data_group_create(pk=10, request=request)
self.assertEqual(resp.status_code, 302,
"Should be redirected to new datagroup detail page")
newdg_pk = resolve(resp.url).kwargs["pk"]
# does the datagroup in the ORM contain the new data docs?
newdg = DataGroup.objects.get(pk=newdg_pk)
newdds = DataDocument.objects.filter(data_group=newdg)
self.assertEqual(newdds.count(), 1,
"There should be one new data document")
# Does the data document page include a link to the csv?
resp = self.client.get(f"/datadocument/%s/" % newdds[0].id)
# Does the response include a link to the data document's file?
self.assertContains(resp, f"pdf/document_%s.html" % newdds[0].id)
def testBadGroupTypeInCSV(self):
csv_string_bad = (
"filename,title,document_type,url,organization\n"
"0bf5755e-3a08-4024-9d2f-0ea155a9bd17.pdf,NUTRA NAIL,HH,, \n"
"0c68ab16-2065-4d9b-a8f2-e428eb192465.pdf,Body Cream,HH,, \n")
data = io.StringIO(csv_string_bad)
csv_len = len(csv_string_bad)
sample_csv = InMemoryUploadedFile(
data,
field_name="csv",
name="register_records.csv",
content_type="text/csv",
size=csv_len,
charset="utf-8",
)
form_data = {
"name": ["Composition Type Group"],
"description": ["test data group"],
"group_type": ["2"], # Composition
"downloaded_by": ["1"],
"downloaded_at": ["08/02/2018"],
"download_script": ["1"],
"data_source": ["10"],
}
request = self.factory.post(path="/datagroup/new", data=form_data)
request.FILES["csv"] = sample_csv
middleware = SessionMiddleware()
middleware.process_request(request)
request.session.save()
middleware = MessageMiddleware()
middleware.process_request(request)
request.session.save()
request.user = User.objects.get(username="******")
request.session = {}
request.session["datasource_title"] = "Walmart"
request.session["datasource_pk"] = 10
resp = views.data_group_create(pk=10, request=request)
# the upload form should be invalid
self.assertIn(
"The document type must be allowed by the parent data group.".
encode(),
resp.content,
)
def test_datagroup_create_dupe_filename(self):
csv_string = (
"filename,title,document_type,url,organization\n"
"0bf5755e-3a08-4024-9d2f-0ea155a9bd17.pdf,NUTRA NAIL,MS,, \n"
"0bf5755e-3a08-4024-9d2f-0ea155a9bd17.pdf,Body Cream,MS,, \n")
data = io.StringIO(csv_string)
sample_csv = InMemoryUploadedFile(
data,
field_name="csv",
name="register_records.csv",
content_type="text/csv",
size=len(csv_string),
charset="utf-8",
)
form_data = {
"name": ["Walmart MSDS Test Group"],
"description": ["test data group"],
"group_type": ["2"],
"downloaded_by": [str(User.objects.get(username="******").pk)],
"downloaded_at": ["08/02/2018"],
"download_script": ["1"],
"data_source": ["10"],
}
request = self.factory.post(path="/datagroup/new/", data=form_data)
request.FILES["csv"] = sample_csv
middleware = SessionMiddleware()
middleware.process_request(request)
request.session.save()
middleware = MessageMiddleware()
middleware.process_request(request)
request.session.save()
request.user = User.objects.get(username="******")
request.session = {}
request.session["datasource_title"] = "Walmart"
request.session["datasource_pk"] = 10
resp = views.data_group_create(request=request, pk=10)
self.assertContains(
resp,
"Duplicate "filename" values for ""
"0bf5755e-3a08-4024-9d2f-0ea155a9bd17.pdf" are not allowed.",
)
def testGoodGroupTypeInCSV(self):
csv_string_good = (
"filename,title,document_type,url,organization\n"
"0bf5755e-3a08-4024-9d2f-0ea155a9bd17.pdf,NUTRA NAIL,MS,, \n"
"0c68ab16-2065-4d9b-a8f2-e428eb192465.pdf,Body Cream,MS,, \n")
data = io.StringIO(csv_string_good)
csv_len = len(csv_string_good)
sample_csv = InMemoryUploadedFile(
data,
field_name="csv",
name="register_records.csv",
content_type="text/csv",
size=csv_len,
charset="utf-8",
)
form_data = {
"name": ["Composition Type Group"],
"description": ["test data group"],
"group_type": ["2"], # Composition
"downloaded_by": ["1"],
"downloaded_at": ["08/02/2018"],
"download_script": ["1"],
"data_source": ["10"],
}
request = self.factory.post(path="/datagroup/new", data=form_data)
request.FILES["csv"] = sample_csv
request.user = User.objects.get(username="******")
request.session = {}
request.session["datasource_title"] = "Walmart"
request.session["datasource_pk"] = 10
resp = views.data_group_create(pk=10, request=request)
self.assertEqual(resp.status_code, 302,
"Should be redirected to new datagroup detail page")
# does the datagroup in the ORM contain the new data docs?
newdg_pk = resolve(resp.url).kwargs["pk"]
newdg = DataGroup.objects.get(pk=newdg_pk)
newdds = DataDocument.objects.filter(data_group=newdg)
self.assertEqual(newdds.count(), 2,
"There should be two new data documents")
def testGoodGroupTypeInCSV(self):
csv_string_good = ("filename,title,document_type,url,organization\n"
"0bf5755e-3a08-4024-9d2f-0ea155a9bd17.pdf,NUTRA NAIL,MS,, \n"
"0c68ab16-2065-4d9b-a8f2-e428eb192465.pdf,Body Cream,MS,, \n")
# DocumentType.objects.all().filter(group_type__title='Composition').values('id', 'title')
# assigning the (compatible) MSDS document type in the csv
data = io.StringIO(csv_string_good)
csv_len = len(csv_string_good)
sample_csv = InMemoryUploadedFile(data,
field_name='csv',
name='register_records.csv',
content_type='text/csv',
size=csv_len,
charset='utf-8')
form_data= {'name': ['Composition Type Group'],
'description': ['test data group'],
'group_type': ['2'], # Composition
'downloaded_by': ['1'],
'downloaded_at': ['08/02/2018'],
'download_script': ['1'],
'data_source': ['10']}
request = self.factory.post(path='/datagroup/new', data=form_data)
request.FILES['csv'] = sample_csv
request.user = User.objects.get(username='******')
request.session={}
request.session['datasource_title'] = 'Walmart'
request.session['datasource_pk'] = 10
resp = views.data_group_create(pk = 10, request=request)
self.assertEqual(resp.status_code,302,
"Should be redirected to new datagroup detail page")
# does the datagroup in the ORM contain the new data docs?
newdg_pk = resolve(resp.url).kwargs['pk']
newdg = DataGroup.objects.get(pk=newdg_pk)
newdds = DataDocument.objects.filter(data_group=newdg)
self.assertEqual(newdds.count(),2,'There should be two new data documents')
def test_csv_line_endings(self):
csv_string = (
"filename,title,document_type,url,organization\r"
"0bf5755e-3a08-4024-9d2f-0ea155a9bd17.pdf,NUTRA NAIL,MS,, \r"
"0c68ab16-2065-4d9b-a8f2-e428eb192465.pdf,Body Cream,MS,, \r\n")
data = io.StringIO(csv_string)
sample_csv = InMemoryUploadedFile(
data,
field_name="csv",
name="register_records.csv",
content_type="text/csv",
size=len(csv_string),
charset="utf-8",
)
form_data = {
"name": ["Walmart MSDS Test Group"],
"description": ["test data group"],
"group_type": ["2"],
"downloaded_by": [f"{User.objects.first().pk}"],
"downloaded_at": ["08/02/2018"],
"download_script": ["1"],
"data_source": ["10"],
}
request = self.factory.post(path="/datagroup/new/", data=form_data)
request.FILES["csv"] = sample_csv
middleware = SessionMiddleware()
middleware.process_request(request)
request.session.save()
middleware = MessageMiddleware()
middleware.process_request(request)
request.session.save()
request.user = User.objects.get(username="******")
request.session = {"datasource_title": "Walmart", "datasource_pk": 10}
resp = views.data_group_create(request=request, pk=10)
dg = DataGroup.objects.filter(name="Walmart MSDS Test Group")
self.assertTrue(resp.status_code == 302, "Redirect to detail page")
self.assertTrue(dg.exists(), "Group should be created")
def test_datagroup_create(self):
long_fn = "a filename that is too long " * 10
csv_string = (
"filename,title,document_type,url,organization\n"
"0bf5755e-3a08-4024-9d2f-0ea155a9bd17.pdf,NUTRA NAIL,MS,, \n"
f"{long_fn},Body Cream,MS,, \n")
data = io.StringIO(csv_string)
sample_csv = InMemoryUploadedFile(
data,
field_name="csv",
name="register_records.csv",
content_type="text/csv",
size=len(csv_string),
charset="utf-8",
)
form_data = {
"name": ["Walmart MSDS Test Group"],
"description": ["test data group"],
"group_type": ["2"],
"downloaded_by": [str(User.objects.get(username="******").pk)],
"downloaded_at": ["08/02/2018"],
"download_script": ["1"],
"data_source": ["10"],
}
request = self.factory.post(path="/datagroup/new/", data=form_data)
request.FILES["csv"] = sample_csv
request.user = User.objects.get(username="******")
middleware = SessionMiddleware()
middleware.process_request(request)
request.session.save()
middleware = MessageMiddleware()
middleware.process_request(request)
request.session.save()
request.session = {}
request.session["datasource_title"] = "Walmart"
request.session["datasource_pk"] = 10
resp = views.data_group_create(request=request, pk=10)
dg_exists = DataGroup.objects.filter(
name="Walmart MSDS Test Group").exists()
self.assertContains(
resp, "filename: Ensure this value has at most 255 characters")
self.assertFalse(dg_exists)
csv_string = (
"filename,title,document_type,url,organization\n"
"0bf5755e-3a08-4024-9d2f-0ea155a9bd17.pdf,NUTRA NAIL,MS,, \n"
"0c68ab16-2065-4d9b-a8f2-e428eb192465.pdf,Body Cream,MS,, \n")
data = io.StringIO(csv_string)
sample_csv = InMemoryUploadedFile(
data,
field_name="csv",
name="register_records.csv",
content_type="text/csv",
size=len(csv_string),
charset="utf-8",
)
request = self.factory.post(path="/datagroup/new", data=form_data)
request.FILES["csv"] = sample_csv
middleware = SessionMiddleware()
middleware.process_request(request)
request.session.save()
middleware = MessageMiddleware()
middleware.process_request(request)
request.session.save()
request.user = User.objects.get(username="******")
request.session = {}
request.session["datasource_title"] = "Walmart"
request.session["datasource_pk"] = 10
resp = views.data_group_create(request=request, pk=10)
self.assertEqual(resp.status_code, 302, "Should be redirecting")
dg = DataGroup.objects.get(name="Walmart MSDS Test Group")
self.assertEqual(f"/datagroup/{dg.pk}/", resp.url,
"Should be redirecting to the proper URL")
# test whether the file system folder was created
self.assertIn(
str(dg.fs_id),
os.listdir(settings.MEDIA_ROOT),
"The data group's UUID should be a folder in MEDIA_ROOT",
)
# In the Data Group Detail Page
resp = self.client.get(f"/datagroup/{dg.pk}/")
# test whether the data documents were created
docs = DataDocument.objects.filter(data_group=dg)
self.assertEqual(len(docs), 2,
"there should be two associated documents")
# test whether the "Download Registered Records" link is like this example
# <a href="/datagroup/a9c7f5a7-5ad4-4f75-b877-a3747f0cc081/download_registered_documents" class="btn btn-secondary">
csv_href = f"/datagroup/{dg.pk}/download_registered_documents/"
self.assertIn(
csv_href,
str(resp._container),
"The data group detail page must contain the right download link",
)
# grab a filename from a data document and see if it's in the csv
doc_fn = docs.first().filename
# test whether the registered records csv download link works
resp_rr_csv = self.client.get(
csv_href) # this object should be of type StreamingHttpResponse
docfound = "not found"
for csv_row in resp_rr_csv.streaming_content:
if doc_fn in str(csv_row):
docfound = "found"
self.assertEqual(
docfound,
"found",
"the document file name should appear in the registered records csv",
)
# Test whether the data document csv download works
# URL on data group detail page: datagroup/docs_csv/{pk}/
dd_csv_href = (f"/datagroup/{dg.pk}/download_documents/"
) # this is an interpreted django URL
resp_dd_csv = self.client.get(dd_csv_href)
for csv_row in resp_dd_csv.streaming_content:
if doc_fn in str(csv_row):
docfound = "found"
self.assertEqual(
docfound,
"found",
"the document file name should appear in the data documents csv",
)
# test uploading one pdf that matches a registered record
doc = DataDocument.objects.filter(data_group_id=dg.pk).first()
pdf = TemporaryUploadedFile(name=doc.filename,
content_type="application/pdf",
size=47,
charset=None)
request = self.factory.post(path="/datagroup/%s" % dg.pk,
data={"uploaddocs-submit": "Submit"})
request.FILES["uploaddocs-documents"] = pdf
middleware = SessionMiddleware()
middleware.process_request(request)
request.session.save()
middleware = MessageMiddleware()
middleware.process_request(request)
request.session.save()
request.user = User.objects.get(username="******")
resp = views.data_group_detail(request=request, pk=dg.pk)
pdf_path = f"{settings.MEDIA_ROOT}{dg.fs_id}/pdf/{doc.get_abstract_filename()}"
self.assertTrue(os.path.exists(pdf_path),
"the stored file should be in MEDIA_ROOT/dg.fs_id")
pdf.close()
def test_datagroup_create(self):
long_fn = 'a filename that is too long ' * 10
csv_string = (
"filename,title,document_type,url,organization\n"
"0bf5755e-3a08-4024-9d2f-0ea155a9bd17.pdf,NUTRA NAIL,UN,, \n"
f"{long_fn},Body Cream,1,, \n")
data = io.StringIO(csv_string)
sample_csv = InMemoryUploadedFile(data,
field_name='csv',
name='register_records.csv',
content_type='text/csv',
size=len(csv_string),
charset='utf-8')
form_data = {
'name': ['Walmart MSDS Test Group'],
'description': ['test data group'],
'group_type': ['1'],
'downloaded_by': [str(User.objects.get(username='******').pk)],
'downloaded_at': ['08/02/2018'],
'download_script': ['1'],
'data_source': ['10']
}
request = self.factory.post(path='/datagroup/new/', data=form_data)
request.FILES['csv'] = sample_csv
request.user = User.objects.get(username='******')
request.session = {}
request.session['datasource_title'] = 'Walmart'
request.session['datasource_pk'] = 10
resp = views.data_group_create(request=request, pk=10)
# print(resp.content)
dg_exists = DataGroup.objects.filter(
name='Walmart MSDS Test Group').exists()
self.assertContains(resp, 'Filename too long')
self.assertFalse(dg_exists, )
# print(dg.__dict__)
csv_string = (
"filename,title,document_type,url,organization\n"
"0bf5755e-3a08-4024-9d2f-0ea155a9bd17.pdf,NUTRA NAIL,UN,, \n"
"0c68ab16-2065-4d9b-a8f2-e428eb192465.pdf,Body Cream,UN,, \n")
data = io.StringIO(csv_string)
sample_csv = InMemoryUploadedFile(data,
field_name='csv',
name='register_records.csv',
content_type='text/csv',
size=len(csv_string),
charset='utf-8')
request = self.factory.post(path='/datagroup/new', data=form_data)
request.FILES['csv'] = sample_csv
request.user = User.objects.get(username='******')
request.session = {}
request.session['datasource_title'] = 'Walmart'
request.session['datasource_pk'] = 10
resp = views.data_group_create(request=request, pk=10)
self.assertEqual(resp.status_code, 302, "Should be redirecting")
dg = DataGroup.objects.get(name='Walmart MSDS Test Group')
self.assertEqual(f'/datagroup/{dg.pk}/', resp.url,
"Should be redirecting to the proper URL")
# test whether the file system folder was created
self.assertIn(
str(dg.fs_id), os.listdir(settings.MEDIA_ROOT),
"The data group's UUID should be a folder in MEDIA_ROOT")
# In the Data Group Detail Page
resp = self.client.get(f'/datagroup/{dg.pk}/')
# test whether the data documents were created
docs = DataDocument.objects.filter(data_group=dg)
self.assertEqual(len(docs), 2,
"there should be two associated documents")
# test whether the "Download Registered Records" link is like this example
# <a href="/datagroup/a9c7f5a7-5ad4-4f75-b877-a3747f0cc081/registered_records.csv" class="btn btn-secondary">
# <span class="oi oi-spreadsheet"></span> Download Registered Records CSV</a>
csv_href = f'/datagroup/{dg.pk}/registered_records.csv'
self.assertIn(
csv_href, str(resp._container),
"The data group detail page must contain the right download link")
# grab a filename from a data document and see if it's in the csv
doc_fn = docs.first().filename
# test whether the registered records csv download link works
resp_rr_csv = self.client.get(
csv_href) # this object should be of type StreamingHttpResponse
docfound = 'not found'
for csv_row in resp_rr_csv.streaming_content:
if doc_fn in str(csv_row):
docfound = 'found'
self.assertEqual(
docfound, 'found',
"the document file name should appear in the registered records csv"
)
# Test whether the data document csv download works
# URL on data group detail page: datagroup/docs_csv/{pk}/
dd_csv_href = f'/datagroup/docs_csv/{dg.pk}/' # this is an interpreted django URL
resp_dd_csv = self.client.get(dd_csv_href)
for csv_row in resp_dd_csv.streaming_content:
if doc_fn in str(csv_row):
docfound = 'found'
self.assertEqual(
docfound, 'found',
"the document file name should appear in the data documents csv")
# test whether the "Download All PDF Documents" link works
dg_zip_href = f'/datagroup/pdfs_zipped/{dg.pk}/' # this is the django-interpreted URL
self.assertIn(
dg_zip_href, str(resp._container),
"The data group detail page must contain the right zip download link"
)
resp_zip = self.client.get(dg_zip_href)
# test uploading one pdf that matches a registered record
f = TemporaryUploadedFile(
name='0bf5755e-3a08-4024-9d2f-0ea155a9bd17.pdf',
content_type='application/pdf',
size=47,
charset=None)
request = self.factory.post(path='/datagroup/%s' % dg.pk,
data={'upload': 'Submit'})
request.FILES['multifiles'] = f
request.user = User.objects.get(username='******')
resp = views.data_group_detail(request=request, pk=dg.pk)
doc = DataDocument.objects.get(title='NUTRA NAIL')
fn = doc.get_abstract_filename()
folder_name = str(dg.fs_id)
stored_file = f'{folder_name}/pdf/{fn}'
pdf_path = f'{settings.MEDIA_ROOT}{stored_file}'
self.assertTrue(os.path.exists(pdf_path),
"the stored file should be in MEDIA_ROOT/dg.fs_id")
f.close()
