Support #372

-   Instead of codes with hyphens, full names of metadata values are in the generated email for the following fields:
    -   `Discipline`
    -   `DataCategory`
    -   `Species`
-   "Name" removed from metadata keys as follows (matching column A):
    -   `InstitutionName` → `Institution`
    -   `LeadPIName` → `LeadPI`
    -   `OrganName` → `Organ`
    -   But: `ProtocolName`, `ProtcolAbbreviatedName`, and `CollectionName` remain untouched
-   LabCAS's weird capitalization enforced as follows (matching column A):
    -   `InstitutionID` → `InstitutionId`
    -   `LeadPIID` → `LeadPIId`
    -   `OrganID` → `OrganId`
    -   `ProtocolID` → `ProtocolId`
    -   But: `PubMedID` remains as is
-   The following fields moved from being appended to the end of the email, to being "fields" in the metadata (column A):
    -   `Instrument`
    -   `Method Details`
    -   These remain as appended to the end of the email (if filled in): comments, biomarkers researched, additional site, type of data being uploaded, other discipline
-   The field `DataDisclaimer` is always filled in; its text can be changed on Wagtail's "Snippets" control panel
-   All permissible values checked (column B)
    -   "Cancers Research Group" dropped from collaborative group names
    -   For `DataCategory`, the `y` stays on `Antibody Microarray` 😌

src/edrnsite.content/src/edrnsite/content/_metadata_collection_form.py

@@ -18,6 +18,23 @@
 from wagtail.contrib.forms.models import EmailFormMixin
 
 
+def _collab_groups():
+    '''Return a vocabulary of collaborative groups.
+
+    Normally we'd want to use CollaborativeGroupSnippet but there's a nasty
+    circular dependency that prevents it from being used here. This form should
+    be in its own module and not in edrnsite.content, which would fix that.
+
+    Also, LabCAS drops the "Cancers Research Group" from each collab group name.
+    '''
+    return [
+        ('breast', 'Breast and Gynecologic'),
+        ('gi', 'G.I. and Other Associated'),
+        ('lung', 'Lung and Upper Aerodigestive'),
+        ('prostate', 'Prostate and Urologic')
+    ]
+
+
 def _species():
     species = (
         'Homo sapiens',
@@ -66,12 +83,7 @@ class MetadataCollectionForm(AbstractEDRNForm):
     cg = forms.ChoiceField(
         label='Collaborative Group', help_text='Select the collaborative research group',
         widget=forms.RadioSelect,
-        choices=(
-            ('breast-gyn', 'Breast & Gynecological Cancers Research Group'),
-            ('colorect-gi', 'Colorectal & Other GI Cancers Research Group'),
-            ('lung', 'Lung & Upper Aerodigestive Cancers Research Group'),
-            ('prostate', 'Prostate & Other Urologic Cancers Research Group'),
-        )
+        choices=_collab_groups()
     )
     discipline = forms.MultipleChoiceField(label='Discipline', widget=forms.CheckboxSelectMultiple, choices=discipline_choices)
     other_discipline = forms.CharField(
@@ -177,38 +189,50 @@ def render_email(self, form):
         site_id, pi_id = data['pi_site'].split('-')
 
         pi = Person.objects.filter(personID=pi_id).first()
-        cp.set('Collection', 'LeadPIID', pi_id)
-        cp.set('Collection', 'LeadPIName', pi.title)
+        cp.set('Collection', 'LeadPIId', pi_id)
+        cp.set('Collection', 'LeadPI', pi.title)
 
         cp.set('Collection', 'DataCustodian', data['custodian'])
         cp.set('Collection', 'DataCustodianEmail', data['custodian_email'])
 
         site = Site.objects.filter(dmccSiteID=site_id).first()
-        cp.set('Collection', 'InstitutionID', site_id)
-        cp.set('Collection', 'InstitutionName', site.title)
+        cp.set('Collection', 'InstitutionId', site_id)
+        cp.set('Collection', 'Institution', site.title)
 
         protocol = Protocol.objects.filter(identifier=data['protocol']).first()
-        cp.set('Collection', 'ProtocolID', self._code(data['protocol']))
+        cp.set('Collection', 'ProtocolId', self._code(data['protocol']))
         cp.set('Collection', 'ProtocolName', protocol.title)
         cp.set('Collection', 'ProtocolAbbreviatedName', protocol.abbreviation)
 
         if data['discipline']:
-            cp.set('Collection', 'Discipline', '|'.join(data['discipline']))
-        cp.set('Collection', 'DataCategory', data['category'])
+            disc_names = {i[0]: i[1] for i in discipline_choices()}
+            discs = [disc_names[i] for i in data['discipline']]
+            cp.set('Collection', 'Discipline', '|'.join(discs))
+        cp.set(
+            'Collection', 'DataCategory',
+            {i[0]: i[1] for i in data_category_choices()}[data['category']]
+        )
 
         bs = BodySystem.objects.filter(identifier=data['organ']).first()
-        cp.set('Collection', 'OrganID', self._code(data['organ']))
-        cp.set('Collection', 'OrganName', bs.title)
+        cp.set('Collection', 'OrganId', self._code(data['organ']))
+        cp.set('Collection', 'Organ', bs.title)
+
+        cp.set(
+            'Collection', 'CollaborativeGroup',
+            {i[0]: i[1] for i in _collab_groups()}[data['cg']]
+        )
 
-        cp.set('Collection', 'CollaborativeGroup', data['cg'])
         if data['results']: cp.set('Collection', 'ResultsAndConclusionSummary', data['results'])
         if data['pub_med_id']: cp.set('Collection', 'PubMedID', data['pub_med_id'])
-        if data['reference_url']: cp.set('Collection', 'ReferenceURL', data['reference_url'])
+        if data['reference_url']: cp.set('Collection', 'ReferenceURLLink', data['reference_url'])
         if data['reference_url_description']:
             cp.set('Collection', 'ReferenceURLDescription', data['reference_url_description'])
         if data['reference_url_other']: cp.set('Collection', 'ReferenceURLOther', data['reference_url_other'])
         cp.set('Collection', 'Consortium', 'EDRN')
-        cp.set('Collection', 'Species', data['species'])
+        cp.set(
+            'Collection', 'Species',
+            {i[0]: i[1] for i in _species()}[data['species']]
+        )
 
         if not data['private']: cp.set('Collection', 'OwnerPrincipal', ALL_USERS_DN)
         if data['access_groups']:
@@ -220,6 +244,18 @@ def render_email(self, form):
         if data['doi']: cp.set('Collection', 'DOI', data['doi'])
         if data['doi_url']: cp.set('Collection', 'DOIURL', data['doi_url'])
 
+        # Always add the data disclaimer #372
+        from .models import BoilerplateSnippet
+        disclaimer = BoilerplateSnippet.objects.filter(bp_code='data-disclaimer').first()
+        if not disclaimer:
+            disclaimer_text = '«No data disclaimer snippet found in portal snippets»'
+        else:
+            disclaimer_text = disclaimer.text
+        cp.set('Collection', 'DataDisclaimer', disclaimer_text)
+
+        if data['instrument']: cp.set('Collection', 'Instrument', data['instrument'])
+        if data['method_details']: cp.set('Collection', 'MethodDetails', data['method_details'])
+
         buffer = StringIO()
         cp.write(buffer)
 
@@ -247,18 +283,6 @@ def render_email(self, form):
             buffer.write('\n\nThe following was entered into the "type of data" field:\n\n')
             buffer.write(data['type_of_data'])
 
-        if data['method_details']:
-            buffer.write('\n\n\n')
-            buffer.write('-' * 40)
-            buffer.write('\n\nThe following was entered into the "method details" field:\n\n')
-            buffer.write(data['method_details'])
-
-        if data['instrument']:
-            buffer.write('\n\n\n')
-            buffer.write('-' * 40)
-            buffer.write('\n\nThe following was entered into the "instrument" field:\n\n')
-            buffer.write(data['instrument'])
-
         if data['other_discipline']:
             buffer.write('\n\n\n')
             buffer.write('-' * 40)

src/edrnsite.content/src/edrnsite/content/base_forms.py

@@ -61,12 +61,12 @@ def discipline_choices():
     '''Vocabulary for choices for disciplines.'''
     return [
         ('genomics', 'Genomics'),
+        ('immunology', 'Immunology'),
         ('metabolomics', 'Metabolomics'),
-        ('proteomics', 'Proteomics'),
+        ('pathology', 'Pathology'),
         ('pathology-images', 'Pathology Images'),
+        ('proteomics', 'Proteomics'),
         ('radiology', 'Radiology'),
-        ('immunology', 'Immunology'),
-        ('pathology', 'Pathology'),
         ('other', 'Other'),
     ]
 

src/edrnsite.content/src/edrnsite/content/management/commands/edrn_data_disclaimer.py

@@ -0,0 +1,34 @@
+# encoding: utf-8
+
+'''😌 EDRN Site Content: add data disclaimer snippet.'''
+
+from django.core.management.base import BaseCommand
+from django.db.utils import IntegrityError
+from edrnsite.content.models import BoilerplateSnippet
+
+
+_default_data_disclaimer = '''Data and information released from the National Cancer Institute (NCI) are provided on
+an "AS IS" basis, without warranty of any kind, including without limitation the warranties of merchantability, fitness
+for a particular purpose and non-infringement. Availability of this data and information does not constitute scientific
+publication. Data and/or information may contain errors or be incomplete. NCI and its employees make no representation
+or warranty, express or implied, including without limitation any warranties of merchantability or fitness for a
+particular purpose or warranties as to the identity or ownership of data or information, the quality, accuracy or
+completeness of data or information, or that the use of such data or information will not infringe any patent,
+intellectual property or proprietary rights of any party. NCI shall not be liable for any claim for any loss, harm,
+illness or other damage or injury arising from access to or use of data or information, including without limitation
+any direct, indirect, incidental, exemplary, special or consequential damages, even if advised of the possibility of
+such damages. In accordance with scientific standards, appropriate acknowledgment of NCI should be made in any
+publications or other disclosures concerning data or information made available by NCI.'''
+
+
+class Command(BaseCommand):
+    help = 'Add the data disclaimer snippet'
+
+    def handle(self, *args, **options):
+        try:
+            self.stdout.write('Adding data disclaimer snippet')
+            BoilerplateSnippet.objects.get_or_create(
+                bp_code='data-disclaimer', text=_default_data_disclaimer
+            )
+        except IntegrityError:
+            pass

support/cbiit-deploy-prod.sh

@@ -145,7 +145,8 @@ docker compose --project-name edrn start portal" || exit 1
 echo ""
 echo "🆙 Applying upgrades"
 ssh -q $USER@$WEBSERVER "cd $WEBROOT ; \
-docker compose --project-name edrn exec portal /usr/bin/django-admin copy_daily_hits_from_wagtailsearch" || exit 1
+docker compose --project-name edrn exec portal /usr/bin/django-admin copy_daily_hits_from_wagtailsearch &&\
+docker compose --project-name edrn exec portal /usr/bin/django-admin edrn_data_disclaimer" || exit 1
 
 echo ""
 echo "🤷‍♀️ Final portal restart and restart of search engine"

support/cbiit-deploy.sh

@@ -146,7 +146,9 @@ docker compose --project-name edrn start portal" || exit 1
 echo ""
 echo "🆙 Applying upgrades"
 ssh -q $USER@$WEBSERVER "cd $WEBROOT ; \
-docker compose --project-name edrn exec portal /usr/bin/django-admin copy_daily_hits_from_wagtailsearch" || exit 1
+docker compose --project-name edrn exec portal /usr/bin/django-admin copy_daily_hits_from_wagtailsearch &&\
+docker compose --project-name edrn exec portal /usr/bin/django-admin edrn_data_disclaimer" || exit 1
+
 
 echo ""
 echo "🤷‍♀️ Final portal restart and restart of search engine"

support/devrebuild.sh

@@ -56,6 +56,7 @@ bzip2 --decompress --stdout edrn.sql.bz2 | psql --dbname=edrn --echo-errors --qu
 ./manage.sh migrate
 ./manage.sh copy_daily_hits_from_wagtailsearch  # Wagtail 5
 ./manage.sh collectstatic --no-input --clear --link
+./manage.sh edrn_data_disclaimer
 ./manage.sh edrndevreset
 
 # Add additional upgrade steps here: