Plone upgrade, conversion from alpine, and resolve #18

Author: nutjob4life

Dockerfile

@@ -3,21 +3,16 @@
 #
 # Defines the image for the CancerDataExpo
 
-FROM plone:5.2.2-alpine
+FROM plone:5.2.9
 
-ENV numpy=1.19.3
+ENV numpy=1.23.4
 
 COPY site.cfg /plone/instance/
 COPY src/ /plone/instance/src/
 COPY etc/ /plone/instance/etc/
 
 RUN : &&\
-    build_deps="gcc musl-dev" &&\
-    apk update --quiet &&\
-    apk add --quiet --virtual /build $build_deps &&\
     pip --quiet install numpy==${numpy} &&\
     buildout -c site.cfg &&\
     find /plone -not -user plone -exec chown plone:plone {} \+ &&\
-    apk del --quiet /build &&\
-    rm -rf /var/cache/apk/* &&\
     :

README.md

@@ -54,12 +54,12 @@ The answer will then be in the result element of the response element of the env
 
 ## 🔧 Developing
 
-**👉 Note:** Plone 5.2.2 (used here) is not compatible with any Python newer than 3.8. Stick with 3.8.
+**👉 Note:** Plone 5.2.9 (used here) is not compatible with any Python newer than 3.8. Stick with 3.8.
 
 Do the following:
 ```console
 python3.8 -m venv venv
-venv/bin/pip install --upgrade pip build wheel zc.buildout setuptools==42.0.2 numpy==1.19.3
+venv/bin/pip install --upgrade pip build wheel zc.buildout setuptools==42.0.2 numpy==1.23.4
 venv/bin/buildout -c dev.cfg
 ```
 

etc/versions/dists.cfg

@@ -14,7 +14,7 @@
 #
 # That's it (for now).
 [buildout]
-extends = https://dist.plone.org/release/5.2.2/versions.cfg
+extends = https://dist.plone.org/release/5.2.9/versions.cfg
 
 
 # Software Distributions to Compile/Make/Install

etc/versions/known-good-versions.cfg

@@ -223,3 +223,192 @@ suds2 = 0.7.1
 # Required by:
 # unittest2==1.1.0
 traceback2 = 1.4.0
+
+# Added by buildout at 2022-12-05 16:58:47.176461
+biothings-client = 0.2.6
+collective.recipe.backup = 4.2.0
+isort = 5.10.1
+modernize = 0.8.0
+mr.scripty = 1.0
+
+# Required by:
+# edrn.summarizer==0.0.8
+biopython = 1.80
+
+# Required by:
+# edrn.rdf==1.3.8
+# edrn.summarizer==0.0.8
+collective.autopermission = 1.0b2
+
+# Required by:
+# modernize==0.8.0
+fissix = 21.11.13
+
+# Required by:
+# rdflib==4.2.2
+isodate = 0.6.1
+
+# Required by:
+# edrn.summarizer==0.0.8
+mygene = 3.2.2
+
+# Required by:
+# edrn.rdf==1.3.8
+pysolr = 3.9.0
+
+# Required by:
+# edrn.rdf==1.3.8
+# edrn.summarizer==0.0.8
+suds2 = 0.7.1
+
+# Required by:
+# python-dotenv==0.15.0
+typing = 3.10.0.0
+
+# Added by buildout at 2022-12-05 17:12:03.918426
+biothings-client = 0.2.6
+collective.recipe.backup = 4.2.0
+isort = 5.10.1
+modernize = 0.8.0
+mr.scripty = 1.0
+
+# Required by:
+# edrn.summarizer==0.0.8
+biopython = 1.80
+
+# Required by:
+# edrn.rdf==1.3.8
+# edrn.summarizer==0.0.8
+collective.autopermission = 1.0b2
+
+# Required by:
+# modernize==0.8.0
+fissix = 21.11.13
+
+# Required by:
+# rdflib==4.2.2
+isodate = 0.6.1
+
+# Required by:
+# edrn.summarizer==0.0.8
+mygene = 3.2.2
+
+# Required by:
+# edrn.rdf==1.3.8
+pysolr = 3.9.0
+
+# Required by:
+# edrn.rdf==1.3.8
+# edrn.summarizer==0.0.8
+suds2 = 0.7.1
+
+# Added by buildout at 2022-12-06 09:35:44.943510
+biothings-client = 0.2.6
+collective.recipe.backup = 4.2.0
+isort = 5.10.1
+modernize = 0.8.0
+mr.scripty = 1.0
+
+# Required by:
+# edrn.summarizer==0.0.8
+biopython = 1.80
+
+# Required by:
+# edrn.rdf==1.3.8
+# edrn.summarizer==0.0.8
+collective.autopermission = 1.0b2
+
+# Required by:
+# modernize==0.8.0
+fissix = 21.11.13
+
+# Required by:
+# rdflib==6.2.0
+isodate = 0.6.1
+
+# Required by:
+# edrn.summarizer==0.0.8
+mygene = 3.2.2
+
+# Required by:
+# edrn.rdf==1.3.8
+pysolr = 3.9.0
+
+# Required by:
+# edrn.rdf==1.3.8
+# edrn.summarizer==0.0.8
+suds2 = 0.7.1
+
+# Added by buildout at 2022-12-06 09:44:08.666120
+biothings-client = 0.2.6
+collective.recipe.backup = 4.2.0
+isort = 5.10.1
+modernize = 0.8.0
+mr.scripty = 1.0
+
+# Required by:
+# edrn.summarizer==0.0.8
+biopython = 1.80
+
+# Required by:
+# edrn.rdf==1.3.8
+# edrn.summarizer==0.0.8
+collective.autopermission = 1.0b2
+
+# Required by:
+# modernize==0.8.0
+fissix = 21.11.13
+
+# Required by:
+# rdflib==5.0.0
+isodate = 0.6.1
+
+# Required by:
+# edrn.summarizer==0.0.8
+mygene = 3.2.2
+
+# Required by:
+# edrn.rdf==1.3.8
+pysolr = 3.9.0
+
+# Required by:
+# edrn.rdf==1.3.8
+# edrn.summarizer==0.0.8
+suds2 = 0.7.1
+
+# Added by buildout at 2022-12-06 10:22:10.706859
+biothings-client = 0.2.6
+collective.recipe.backup = 4.2.0
+isort = 5.10.1
+modernize = 0.8.0
+mr.scripty = 1.0
+
+# Required by:
+# edrn.summarizer==0.0.8
+biopython = 1.80
+
+# Required by:
+# edrn.rdf==1.3.8
+# edrn.summarizer==0.0.8
+collective.autopermission = 1.0b2
+
+# Required by:
+# modernize==0.8.0
+fissix = 21.11.13
+
+# Required by:
+# rdflib==6.2.0
+isodate = 0.6.1
+
+# Required by:
+# edrn.summarizer==0.0.8
+mygene = 3.2.2
+
+# Required by:
+# edrn.rdf==1.3.8
+pysolr = 3.9.0
+
+# Required by:
+# edrn.rdf==1.3.8
+# edrn.summarizer==0.0.8
+suds2 = 0.7.1

etc/zope.cfg

@@ -93,7 +93,6 @@ eggs =
     plone.testing
     plone.app.testing
     plone.app.robotframework
-    unittest2
     plone.app.upgrade
 defaults = ['--auto-color', '--auto-progress', '--verbose']
 

src/edrn.rdf/edrn/rdf/README.rst

@@ -311,7 +311,7 @@ And now::
     'application/rdf+xml'
     >>> import rdflib
     >>> graph = rdflib.Graph()
-    >>> graph.parse(data=browser.contents)
+    >>> graph.parse(data=browser.contents, format='xml')
     <Graph identifier=...(<class 'rdflib.graph.Graph'>)>
     >>> len(graph)
     68
@@ -431,7 +431,7 @@ And now::
 
     >>> browser.open(portalURL + '/a-simple-source/@@rdf')
     >>> graph = rdflib.Graph()
-    >>> graph.parse(data=browser.contents)
+    >>> graph.parse(data=browser.contents, format='xml')
     <Graph identifier=...(<class 'rdflib.graph.Graph'>)>
     >>> len(graph)
     124
@@ -541,7 +541,7 @@ And now for the RDF::
 
     >>> browser.open(portalURL + '/a-simple-source/@@rdf')
     >>> graph = rdflib.Graph()
-    >>> graph.parse(data=browser.contents)
+    >>> graph.parse(data=browser.contents, format='xml')
     <Graph identifier=...(<class 'rdflib.graph.Graph'>)>
     >>> len(graph)
     31809
@@ -672,7 +672,7 @@ And now for the RDF::
 
     >>> browser.open(portalURL + '/a-committee-source/@@rdf')
     >>> graph = rdflib.Graph()
-    >>> graph.parse(data=browser.contents)
+    >>> graph.parse(data=browser.contents, format='xml')
     <Graph identifier=...(<class 'rdflib.graph.Graph'>)>
     >>> len(graph)
     298
@@ -804,7 +804,7 @@ And now for the RDF::
 
     >>> browser.open(portalURL + '/a-protocol-source/@@rdf')
     >>> graph = rdflib.Graph()
-    >>> graph.parse(data=browser.contents)
+    >>> graph.parse(data=browser.contents, format='xml')
     <Graph identifier=...(<class 'rdflib.graph.Graph'>)>
     >>> len(graph) > 9422
     True
@@ -969,7 +969,7 @@ And now for the RDF::
 
     >>> browser.open(portalURL + '/a-biomuta-source/@@rdf')
     >>> graph = rdflib.Graph()
-    >>> graph.parse(data=browser.contents)
+    >>> graph.parse(data=browser.contents, format='xml')
     <Graph identifier=...(<class 'rdflib.graph.Graph'>)>
     >>> len(graph)
     131187

src/edrn.rdf/edrn/rdf/labcascollectionrdfgenerator.py

@@ -86,11 +86,11 @@ def generateGraph(self):
         context = aq_inner(self.context)
         graph = rdflib.Graph()
         solr = Solr(context.labcasSolrURL + '/datasets', auth=(context.username, context.password))
-        numDatasets = solr.search(q='*:*', rows=0).hits
+        numDatasets = solr.search(q='Consortium:EDRN', rows=0).hits
         solr = Solr(context.labcasSolrURL + '/files', auth=(context.username, context.password))
-        numFiles = solr.search(q='*:*', rows=0).hits
+        numFiles = solr.search(q='Consortium:EDRN', rows=0).hits
         solr = Solr(context.labcasSolrURL + '/collections', auth=(context.username, context.password))
-        results = solr.search(q='*:*', rows=999999)  # 😮 TODO This'll fail once we get to a million collections
+        results = solr.search(q='Consortium:EDRN', rows=999999)  # 😮 TODO This'll fail once we get to a million collections
         numCollections = results.hits
         for i in results:
             collectionID, name, consortia = i.get('id'), i.get('CollectionName', '«unknown»'), i.get('Consortium', [])

src/edrn.rdf/edrn/rdf/rdfupdater.py

@@ -41,9 +41,13 @@ def updateRDF(self):
         # Is there an active file?
         if context.approvedFile:
             # Is it identical to what we just generated?
-            current = Graph().parse(data=context.approvedFile.to_object.file.data)
-            if isomorphic(graph, current):
-                raise NoUpdateRequired(context)
+            try:
+                current = Graph().parse(data=context.approvedFile.to_object.file.data, format='xml')
+                if isomorphic(graph, current):
+                    raise NoUpdateRequired(context)
+            except AttributeError:
+                # File not found
+                pass
 
         # Create a new file and set it active
         # TODO: Add validation steps here

src/edrn.rdf/setup.py

@@ -31,7 +31,7 @@
     'plone.app.relationfield',
     'plone.behavior',
     'Products.CMFPlone',
-    'rdflib==4.2.2',
+    'rdflib==6.2.0',
     'setuptools',
     'z3c.relationfield',
     'suds2',

src/edrn.summarizer/edrn/summarizer/biomarkersummarizergenerator.py

@@ -16,7 +16,7 @@
 from zope import schema
 from zope.component import queryUtility
 from plone.i18n.normalizer.interfaces import IIDNormalizer
-import jsonlib
+import json
 
 _typeURI                                 = URIRef('http://www.w3.org/1999/02/22-rdf-syntax-ns#type')
 _bmOrganDataTypeURI                      = URIRef('http://edrn.nci.nih.gov/rdf/rdfs/bmdb-1.0.0#BiomarkerOrganData')
@@ -108,7 +108,7 @@ def generateJson(self):
             raise RDFIngestException(_('This generator folder lacks one or both of its RDF source URLs.'))
         normalizerFunction = queryUtility(IIDNormalizer).normalize
         graph = ConjunctiveGraph()
-        graph.parse(URLInputSource(rdfDataSource))
+        graph.parse(URLInputSource(rdfDataSource), format='xml')
         statements = self._parseRDF(graph)
 
         biomarkerTypeFreq = {}
@@ -141,11 +141,11 @@ def generateJson(self):
 
         # Add organ-specific information
         graph = ConjunctiveGraph()
-        graph.parse(URLInputSource(bmoDataSource))
+        graph.parse(URLInputSource(bmoDataSource), format='xml')
         organStatements = self._parseRDF(graph)
         self.addOrganSpecificInformation(allBiomarkers, organStatements, biomarkerOrganFreq)
 
         jsondata = self.generateOrganTypeStats(biomarkerTypeFreq,biomarkerOrganFreq)
 
         # C'est tout.
-        return jsonlib.write(jsondata)
+        return json.dumps(jsondata)