Fix transform join subcommand

CHANGELOG.md

@@ -1,10 +1,16 @@
 # Change log
 
+## Release 0.8.4 (2024-03-04)
+
+Bug fixes:
+
+- Fix transform join subcommand to produce vocpub-4.7-conform turtle file. #213
+
 ## Release 0.8.3 (2024-02-28)
 
 Bug fixes:
 
-- Fix writing to wrong file location for sub-command "join" with "--outbox" option. #211, #212 
+- Fix writing to wrong file location for sub-command "join" with "--outbox" option. #211, #212
 - Fix clearing of cells with hyperlinks in xlsx by openpyxl. #209, #210
 
 ## Release 0.8.2 (2024-02-21)

pyproject.toml

@@ -168,12 +168,19 @@ exclude = [
     "*.egg",
     ".*",
 ]
+
+# Assume Python 3.8
+target-version = "py38"
+
+# Same as Black.
+line-length = 88
+
+[tool.ruff.lint]
+
 ignore = [
     "B905",  # zip() without an explicit strict= parameter set. (requires python >= 3.10)
     "E501",  # line too long
 ]
-# Same as Black.
-line-length = 88
 
 # Avoid trying to fix these violations
 unfixable = [
@@ -218,19 +225,17 @@ select = [
     # NumPy-specific rules (NPY)
     "RUF",  # Ruff-specific rules
 ]
-# Assume Python 3.8
-target-version = "py38"
 
-[tool.ruff.per-file-ignores]
+[tool.ruff.lint.per-file-ignores]
 "tests/*.py" = [
   "S101",   # assert in tests is OK
 ]
 
-[tool.ruff.mccabe]
+[tool.ruff.lint.mccabe]
 # Flake8-mccabe uses a default level of 7, ruff of 10.
 max-complexity = 10
 
-[tool.ruff.pep8-naming]
+[tool.ruff.lint.pep8-naming]
 # Allow Pydantic's `@validator` decorator to trigger class method treatment.
 classmethod-decorators = [
   "classmethod",

src/voc4cat/transform.py

@@ -8,7 +8,7 @@
 
 import openpyxl
 from openpyxl.styles import Alignment
-from rdflib import DCTERMS, OWL, RDF, SKOS, XSD, Graph, Literal
+from rdflib import DCTERMS, OWL, RDF, SDO, SKOS, XSD, Graph, Literal, URIRef
 
 from voc4cat import config
 from voc4cat.checks import Voc4catError
@@ -19,6 +19,7 @@
     dag_to_node_levels,
     get_concept_and_level_from_indented_line,
 )
+from voc4cat.models import ORGANISATIONS
 from voc4cat.utils import (
     EXCEL_FILE_ENDINGS,
     RDF_FILE_ENDINGS,
@@ -103,6 +104,42 @@ def join_split_turtle(vocab_dir: Path) -> Graph:
         ):
             graph = autoversion_cs(graph)
         cs_graph += graph
+
+    # TODO The metadata should also be present in a separate ttl-file and
+    #    joined just like the other.
+    # Newer for vocpub profile require creator_/publisher for vocabulary:
+    # Requirement 2.1.6 Each vocabulary MUST have at least one creator,
+    #   indicated using sdo:creator or dcterms:creator predicate and exactly
+    #   one publisher, indicated using sdo:publisher or dcterms:publisher,
+    #   all of which MUST be IRIs indicating instances of sdo:Person,
+    #   or sdo:Organization.
+    # Get the publisher from the first concept scheme
+    publisher = next(cs_graph.triples((None, DCTERMS.publisher, None)))[2]
+    tg = Graph()
+    org = ORGANISATIONS.get(publisher, URIRef(publisher))
+    tg.add((org, RDF.type, SDO.Organization))
+    tg.add(
+        (
+            org,
+            SDO.name,
+            # should be name but there is no field in the template 0.43
+            Literal(
+                ORGANISATIONS.get(publisher, publisher),
+            ),
+        )
+    )
+    tg.add(
+        (
+            org,
+            SDO.url,
+            Literal(
+                ORGANISATIONS.get(publisher, publisher),
+                datatype=URIRef(XSD.anyURI),
+            ),
+        )
+    )
+    cs_graph += tg
+
     cs_graph.serialize(destination=vocab_dir.with_suffix(".ttl"), format="turtle")
     return cs_graph