Add citation generation and pushed python to 3.9

.github/workflows/reeco_initialize.yml

@@ -92,6 +92,12 @@ jobs:
           pip install pysparql-anything
           python build_rdf_data_files.py
 
+      - name: build Citation data CSV
+        id: build_citation_data_file
+        run: |
+          pip install pysparql-anything
+          python build_citation_data_file.py
+
       - name: get current date
         id: date
         run: echo "::set-output name=date::$(date +'%Y_%m_%d_%H-%M')"

build_citation_data_file.py

@@ -0,0 +1,40 @@
+import pysparql_anything as pysa
+import os
+import yaml
+
+config = yaml.load(open('_config.yml','r'), Loader=yaml.Loader)
+namespace = config['rdf']['namespace']
+engine = pysa.SparqlAnything()
+directory = './content/'
+includes = './_includes/cite/'
+for root, dirs, files in os.walk(directory):
+    for filename in files:
+        if not filename.endswith('.md'):
+            continue
+        location = os.path.join(root, filename)
+        if "/.github/" in location:
+            continue
+        #print(location)
+        pre, ext = os.path.splitext(location)
+        output_includes = pre.replace("./content/", includes)
+        output_includes_apa = output_includes + ".cite.apa"
+        output_includes_bib = output_includes + ".cite.bib"
+        #pth = os.path.dirname(os.path.abspath(output))
+        pth_includes = os.path.dirname(os.path.abspath(output_includes))
+        #if not os.path.exists(pth):
+        #    os.makedirs(pth)
+        if not os.path.exists(pth_includes):
+            os.makedirs(pth_includes)
+        d = engine.select(q='./component-citation.sparql', v={'componentFile': location}) #
+        if len(d['results']['bindings']) == 0 or 'component' not in d['results']['bindings'][0]:
+            continue
+        if 'apa' in d['results']['bindings'][0]:
+            apa = d['results']['bindings'][0]['apa']['value']
+            f1 = open(output_includes_apa, 'w')
+            f1.write(apa)
+
+        if 'bibtex' in d['results']['bindings'][0]:
+            bibtex = d['results']['bindings'][0]['bibtex']['value']
+            f1 = open(output_includes_bib, 'w')
+            f1.write(bibtex)
+

component-citation.sparql

@@ -0,0 +1,54 @@
+PREFIX rdf:  <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
+PREFIX fx:   <http://sparql.xyz/facade-x/ns/>
+PREFIX xyz:  <http://sparql.xyz/facade-x/data/>
+PREFIX xsd:  <http://www.w3.org/2001/XMLSchema#>
+PREFIX schema: <https://schema.org/>
+PREFIX fabio: <http://purl.org/spar/fabio/>
+PREFIX frapo: <http://purl.org/cerif/frapo/>
+
+SELECT ?component ?doi ?apa ?bibtex 
+WHERE {
+    SERVICE <x-sparql-anything:> { 
+
+        SERVICE <x-sparql-anything:> { 
+
+        	SERVICE <x-sparql-anything:> {
+
+        		# --> Step 2. extract the YAML fontmatter from files with component annotations
+        		fx:properties fx:location ?_componentFile  .
+        		[] a xyz:YamlFrontMatter ; fx:anySlot ?yaml
+        	}
+
+        	BIND ( ?yaml as ?content ) .
+
+        	#--> Step 3. parse the YAML content
+        	fx:properties fx:content ?content ;
+        		fx:triplifier "io.github.sparqlanything.yaml.YAMLTriplifier" ; fx:blank-nodes "false" ; fx:yaml.allow-duplicate-keys true.
+
+    		{   # Components:
+    			# Id
+    			?x xyz:component-id ?component .
+                ?x xyz:doi ?doi .
+            }
+        }
+        ### curl -LH "Accept: text/x-bibliography; style=apa" https://doi.org/10.1126/science.169.3946.635
+
+        BIND ( CONCAT("https://doi.org/", ?doi) as ?doiLink ) .
+    	fx:properties fx:location ?doiLink ;
+            fx:http.header.accept "text/x-bibliography; style=apa" ;
+            fx:media-type "text/plain" .
+            [] rdf:_1 ?apa
+
+        OPTIONAL{
+            SERVICE <x-sparql-anything:> { 
+            	fx:properties fx:location ?doiLink ;
+                    fx:http.header.accept "text/x-bibliography; style=bibtex" ;
+                    fx:media-type "text/plain" .
+                    [] rdf:_1 ?bibtex
+
+            }
+        }
+    }
+}
+

components-to-rdf.sparql

@@ -103,7 +103,7 @@ WHERE {
 
 		#--> Step 3. parse the YAML content
 		fx:properties fx:content ?content ;
-			fx:triplifier "com.github.sparqlanything.yaml.YAMLTriplifier" ; fx:blank-nodes "false".
+			fx:triplifier "io.github.sparqlanything.yaml.YAMLTriplifier" ; fx:blank-nodes "false".
 
 		#--> Step 4. Query the Ecosystem Schema annotations (when the schema evolves, change only this!)
 		{   # Components:

requirements.txt

@@ -7,19 +7,19 @@ Deprecated==1.2.14
 idna==2.10
 isodate==0.6.1
 pycparser==2.21
-PyGithub==1.59.1
-pyjnius==1.5.0
+PyGithub==1.58.1
+pyjnius==1.6.0
 PyJWT==2.8.0
 PyNaCl==1.5.0
 pyparsing==3.1.1
 pysparql_anything==0.9.0.1
 python-frontmatter==1.0.0
 PyYAML==6.0.1
-rdflib==7.0.0
+rdflib==6.3.1
 reeco==0.0.2.post1697540418
-requests==2.25.1
+requests>=2.25.1
 schema==0.7.5
 six==1.16.0
-tqdm==4.66.1
+tqdm==4.65.0
 urllib3==1.26.16
 wrapt==1.15.0