Ensure standard semweb prefixes are not uppercases, see #70

linkml · Apr 14, 2024 · b38747b · b38747b
1 parent da9a2e6
commit b38747b
Show file tree

Hide file tree

Showing 13 changed files with 54,449 additions and 53,300 deletions.
diff --git a/poetry.lock b/poetry.lock
diff --git a/src/prefixmaps/data/bioregistry.csv b/src/prefixmaps/data/bioregistry.csv
diff --git a/src/prefixmaps/data/bioregistry.upper.csv b/src/prefixmaps/data/bioregistry.upper.csv
diff --git a/src/prefixmaps/data/go.csv b/src/prefixmaps/data/go.csv
@@ -15,6 +15,7 @@ go,EMAPA,http://purl.obolibrary.org/obo/EMAPA_,canonical
 go,ENSEMBL,http://identifiers.org/ensembl/,canonical
 go,FB,http://identifiers.org/flybase/,canonical
 go,FBbt,http://purl.obolibrary.org/obo/FBbt_,canonical
+go,FBdv,http://purl.obolibrary.org/obo/FBdv_,canonical
 go,FMA,http://purl.obolibrary.org/obo/FMA_,canonical
 go,FYPO,http://purl.obolibrary.org/obo/FYPO_,canonical
 go,GeneDB,http://identifiers.org/genedb/,canonical

diff --git a/src/prefixmaps/data/linked_data.csv b/src/prefixmaps/data/linked_data.csv
@@ -12,6 +12,8 @@ linkml,pav,http://purl.org/pav/,canonical
 linkml,prov,http://www.w3.org/ns/prov#,canonical
 linkml,qb,http://purl.org/linked-data/cube#,canonical
 linkml,qudt,http://qudt.org/schema/qudt/,canonical
+linkml,rdf,http://www.w3.org/1999/02/22-rdf-syntax-ns#,canonical
+linkml,rdfs,http://www.w3.org/2000/01/rdf-schema#,canonical
 linkml,schema,http://schema.org/,canonical
 linkml,sh,http://www.w3.org/ns/shacl#,canonical
 linkml,shex,http://www.w3.org/ns/shex#,canonical

diff --git a/src/prefixmaps/data/linked_data.curated.yaml b/src/prefixmaps/data/linked_data.curated.yaml
@@ -1,5 +1,7 @@
 name: linkml
 prefixes:
+  rdf: http://www.w3.org/1999/02/22-rdf-syntax-ns#
+  rdfs: http://www.w3.org/2000/01/rdf-schema#
   linkml: https://w3id.org/linkml/
   dcterms: http://purl.org/dc/terms/
   skos: http://www.w3.org/2004/02/skos/core#
@@ -21,3 +23,5 @@ prefixes:
   shex: http://www.w3.org/ns/shex#
   biolink: https://w3id.org/biolink/vocab/
   foaf: http://xmlns.com/foaf/0.1/
+
+
diff --git a/src/prefixmaps/data/merged.csv b/src/prefixmaps/data/merged.csv
diff --git a/src/prefixmaps/data/merged.monarch.csv b/src/prefixmaps/data/merged.monarch.csv
diff --git a/src/prefixmaps/data/merged.oak.csv b/src/prefixmaps/data/merged.oak.csv
diff --git a/src/prefixmaps/data/obo.csv b/src/prefixmaps/data/obo.csv
@@ -81,6 +81,7 @@ obo,FOBI,http://purl.obolibrary.org/obo/FOBI_,canonical
 obo,FOODON,http://purl.obolibrary.org/obo/FOODON_,canonical
 obo,FOVT,http://purl.obolibrary.org/obo/FOVT_,canonical
 obo,FYPO,http://purl.obolibrary.org/obo/FYPO_,canonical
+obo,GALLONT,http://purl.obolibrary.org/obo/GALLONT_,canonical
 obo,GAZ,http://purl.obolibrary.org/obo/GAZ_,canonical
 obo,GECKO,http://purl.obolibrary.org/obo/GECKO_,canonical
 obo,GENEPIO,http://purl.obolibrary.org/obo/GENEPIO_,canonical
@@ -215,6 +216,7 @@ obo,SCDO,http://purl.obolibrary.org/obo/SCDO_,canonical
 obo,SEP,http://purl.obolibrary.org/obo/SEP_,canonical
 obo,SEPIO,http://purl.obolibrary.org/obo/SEPIO_,canonical
 obo,SIBO,http://purl.obolibrary.org/obo/SIBO_,canonical
+obo,SLSO,http://purl.obolibrary.org/obo/SLSO_,canonical
 obo,SO,http://purl.obolibrary.org/obo/SO_,canonical
 obo,SOPHARM,http://purl.obolibrary.org/obo/SOPHARM_,canonical
 obo,SPD,http://purl.obolibrary.org/obo/SPD_,canonical

diff --git a/src/prefixmaps/data/prefixcc.csv b/src/prefixmaps/data/prefixcc.csv
diff --git a/src/prefixmaps/data/w3id.csv b/src/prefixmaps/data/w3id.csv
diff --git a/src/prefixmaps/ingest/ingest_bioregistry.py b/src/prefixmaps/ingest/ingest_bioregistry.py
@@ -45,7 +45,7 @@ def from_bioregistry(upper=False, canonical_idorg=True, filter_dubious=True) ->
     original namespaces. This can be disabled with ``canonical_idorg=False``.
 
     :param upper: if True, normalize prefix to uppercase
-                    unless a preferred form is stated
+                    unless a preferred form is stated, or it's in the SemWeb collection
     :param canonical_idorg: use the original/canonical identifiers.org PURLs
     :param filter_dubious: skip namespaces that do not match
                     strict namespace regular expression
@@ -71,6 +71,8 @@ def from_bioregistry(upper=False, canonical_idorg=True, filter_dubious=True) ->
         uri_prefix_priority=priority, prefix_priority=prefix_priority
     )
     for record in tqdm(converter.records):
+        # TODO: auto-set preferred to lowercase for SemWeb collection
+        # See https://github.com/linkml/prefixmaps/issues/70
         if record.prefix in SKIP:
             continue
         if filter_dubious and not NAMESPACE_RE.match(record.uri_prefix):