fixes typos in IRIs, resolves #81; updates terms

The following typos in IRIs were fixed using the new SHACL shapes from
previous commit:
- dpv:expiry relation instead of dpv:hasExpiry relation in consent
- dpv:hasConsequenceOn was used as a parent even though it was proposed.
  The term has been promoted to accepted status
- Typos in Technical measures where Crypto- was mistyped as Cryto-

Errors in labels:
- MaintainCreditCheckingDatabase
- MaintainCreditRatingDatabase

The following terms were updated:
- GDPR's legal bases where text has been added from Art.6 and the parent
  terms have been aligned with main spec's legal bases (including
  creation of new terms to match granularity)
- Anonymisation and Pseudonymisation have been changed to be types of
  Deidentification techniques (as the grouping parent concept) to
  distinguish them following discussions in #15
- DPV-LEGAL has laws and DPAs for USA from contributions by @JonathanBowker

documentation-generator/002_parse_csv_to_rdf.py

@@ -693,17 +693,17 @@ def serialize_graph(graph, filepath):
     graph.namespace_manager.bind(prefix, namespace)
 proposed = []
 Location_schema = namedtuple('Legal_Location', (
-    'Term', 'Label', 'ParentTerm', 'Alpha2', 'Alpha3', 'Numeric', 'M49',
+    'term', 'Label', 'Parentterm', 'Alpha2', 'Alpha3', 'Numeric', 'M49',
     'broader', 'narrower', 'created', 'modified', 
     'status', 'contributors', 'resolution'))
 concepts = extract_terms_from_csv(
     f'{IMPORT_CSV_PATH}/legal_Locations.csv', Location_schema)
 for row in concepts:
     if row.status not in VOCAB_TERM_ACCEPT:
-        proposed.append(row.Term)
+        proposed.append(row.term)
         continue
-    term = BASE[row.Term]
-    parent = DPV[row.ParentTerm.replace("dpv:", "")]
+    term = BASE[row.term]
+    parent = DPV[row.Parentterm.replace("dpv:", "")]
     graph.add((term, RDF.type, DPV.Concept))
     graph.add((term, RDF.type, SKOS.Concept))
     graph.add((term, DPV.isInstanceOf, parent))
@@ -819,7 +819,7 @@ def serialize_graph(graph, filepath):
     f'{IMPORT_CSV_PATH}/legal_Authorities.csv', Location_schema)
 for row in concepts:
     if row.status not in VOCAB_TERM_ACCEPT:
-        proposed.append(row.Term)
+        proposed.append(row.term)
         continue
     term = BASE[row.term]
     graph.add((term, RDF.type, DPV.Concept))
@@ -871,7 +871,7 @@ def serialize_graph(graph, filepath):
     f'{IMPORT_CSV_PATH}/legal_EU_EEA.csv', Location_schema)
 for row in concepts:
     if row.status not in VOCAB_TERM_ACCEPT:
-        proposed.append(row.Term)
+        proposed.append(row.term)
         continue
     term = BASE[row.term]
     graph.add((term, RDF.type, DPV.Concept))
@@ -930,7 +930,7 @@ def serialize_graph(graph, filepath):
     f'{IMPORT_CSV_PATH}/legal_EU_Adequacy.csv', Location_schema)
 for row in concepts:
     if row.status not in VOCAB_TERM_ACCEPT:
-        proposed.append(row.Term)
+        proposed.append(row.term)
         continue
     term = BASE[row.term]
     graph.add((term, RDF.type, DPV.Concept))

documentation-generator/002_parse_csv_to_rdf_owl.py

@@ -708,17 +708,17 @@ def serialize_graph(graph, filepath):
     graph.namespace_manager.bind(prefix, namespace)
 proposed = []
 Location_schema = namedtuple('Legal_Location', (
-    'Term', 'Label', 'ParentTerm', 'Alpha2', 'Alpha3', 'Numeric', 'M49',
+    'term', 'Label', 'Parentterm', 'Alpha2', 'Alpha3', 'Numeric', 'M49',
     'broader', 'narrower', 'created', 'modified', 
     'status', 'contributors', 'resolution'))
 concepts = extract_terms_from_csv(
     f'{IMPORT_CSV_PATH}/legal_Locations.csv', Location_schema)
 for row in concepts:
     if row.status not in VOCAB_TERM_ACCEPT:
-        proposed.append(row.Term)
+        proposed.append(row.term)
         continue
-    term = BASE[row.Term]
-    parent = row.ParentTerm.replace("dpv:", "")
+    term = BASE[row.term]
+    parent = row.Parentterm.replace("dpv:", "")
     graph.add((term, RDF.type, DPVO[f'{parent}']))
     graph.add((term, RDF.type, OWL.NamedIndividual))
     graph.add((term, RDFS.isDefinedBy, BASE['']))
@@ -824,7 +824,7 @@ def serialize_graph(graph, filepath):
     f'{IMPORT_CSV_PATH}/legal_Authorities.csv', Location_schema)
 for row in concepts:
     if row.status not in VOCAB_TERM_ACCEPT:
-        proposed.append(row.Term)
+        proposed.append(row.term)
         continue
     term = BASE[row.term]
     graph.add((term, RDF.type, DPVO[f'{row.type.replace("dpv:","")}']))
@@ -871,7 +871,7 @@ def serialize_graph(graph, filepath):
     f'{IMPORT_CSV_PATH}/legal_EU_EEA.csv', Location_schema)
 for row in concepts:
     if row.status not in VOCAB_TERM_ACCEPT:
-        proposed.append(row.Term)
+        proposed.append(row.term)
         continue
     term = BASE[row.term]
     graph.add((term, RDF.type, DPVO[f'{row.type.replace("dpv:","")}']))
@@ -927,7 +927,7 @@ def serialize_graph(graph, filepath):
     f'{IMPORT_CSV_PATH}/legal_EU_Adequacy.csv', Location_schema)
 for row in concepts:
     if row.status not in VOCAB_TERM_ACCEPT:
-        proposed.append(row.Term)
+        proposed.append(row.term)
         continue
     term = BASE[row.term]
     graph.add((term, RDF.type, DPVO.Law))

documentation-generator/002_parse_csv_to_rdf_skos.py

@@ -750,17 +750,17 @@ def serialize_graph(graph, filepath):
     graph.namespace_manager.bind(prefix, namespace)
 proposed = []
 Location_schema = namedtuple('Legal_Location', (
-    'Term', 'Label', 'ParentTerm', 'Alpha2', 'Alpha3', 'Numeric', 'M49',
+    'term', 'Label', 'Parentterm', 'Alpha2', 'Alpha3', 'Numeric', 'M49',
     'broader', 'narrower', 'created', 'modified', 
     'status', 'contributors', 'resolution'))
 concepts = extract_terms_from_csv(
     f'{IMPORT_CSV_PATH}/legal_Locations.csv', Location_schema)
 for row in concepts:
     if row.status not in VOCAB_TERM_ACCEPT:
-        proposed.append(row.Term)
+        proposed.append(row.term)
         continue
-    term = BASE[row.Term]
-    parent = row.ParentTerm.replace("dpv:", "")
+    term = BASE[row.term]
+    parent = row.Parentterm.replace("dpv:", "")
     graph.add((term, RDF.type, DPVS[f'{parent}']))
     graph.add((term, RDF.type, SKOS.Concept))
     graph.add((term, RDFS.isDefinedBy, BASE['']))
@@ -873,7 +873,7 @@ def serialize_graph(graph, filepath):
     f'{IMPORT_CSV_PATH}/legal_Authorities.csv', Location_schema)
 for row in concepts:
     if row.status not in VOCAB_TERM_ACCEPT:
-        proposed.append(row.Term)
+        proposed.append(row.term)
         continue
     term = BASE[row.term]
     graph.add((term, RDF.type, DPVS[f'{row.type.replace("dpv:","")}']))
@@ -924,7 +924,7 @@ def serialize_graph(graph, filepath):
     f'{IMPORT_CSV_PATH}/legal_EU_EEA.csv', Location_schema)
 for row in concepts:
     if row.status not in VOCAB_TERM_ACCEPT:
-        proposed.append(row.Term)
+        proposed.append(row.term)
         continue
     term = BASE[row.term]
     graph.add((term, RDF.type, DPVS[f'{row.type.replace("dpv:","")}']))
@@ -982,7 +982,7 @@ def serialize_graph(graph, filepath):
     f'{IMPORT_CSV_PATH}/legal_EU_Adequacy.csv', Location_schema)
 for row in concepts:
     if row.status not in VOCAB_TERM_ACCEPT:
-        proposed.append(row.Term)
+        proposed.append(row.term)
         continue
     term = BASE[row.term]
     graph.add((term, RDF.type, DPVS.Law))

documentation-generator/801_generate_releases.sh

@@ -38,8 +38,8 @@ zip -q releases/dpv-owl.zip -r dpv-owl
 echo "generated releases/dpv-owl.zip"
 
 # 4. dpv-csv.zip - DPV + Extensions as CSV files
-cp documentation-generator/vocab_csv/dpv_terms_discussion.xlsx releases/dpv.xlsx
-echo "generated releases/dpv.xlsx"
+zip -q releases/dpv-xlsx.zip documentation-generator/vocab_csv/*.xlsx
+echo "generated releases/dpv-xlsx.zip"
 
 # 5. dpv-json.zip - DPV + Extensions as JSON files
 # TODO