fix conflicts, regen artifacts

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "prefixmaps"
-version = "0.1.6"
+version = "0.1.8"
 description = "A python library for retrieving semantic prefix maps"
 readme = "README.md"
 authors = ["cmungall <[email protected]>"]
@@ -24,19 +24,21 @@ homepage = "https://github.com/linkml/prefixmaps"
 
 
 [tool.poetry.dependencies]
-python = "^3.8.0"
+python = "^3.9"
 pyyaml = ">=5.3.1"
 sphinx-rtd-theme = {version = "^1.0.0", extras = ["docs"]}
-Sphinx = {version = "^5.3.0", extras = ["docs"]}
-sphinx-autodoc-typehints = {version = "^1.19.4", extras = ["docs"]}
+Sphinx = {version = "^7.2.6", extras = ["docs"]}
+sphinx-autodoc-typehints = {version = "^1.23.4", extras = ["docs"]}
 sphinx-click = {version = "^4.3.0", extras = ["docs"]}
-myst-parser = {version = "^0.18.1", extras = ["docs"]}
+myst-parser = {version = "^2.0.0", extras = ["docs"]}
 click = ">=8.1.3"
 requests = {version = "^2.28.1", extras = ["refresh"]}
-bioregistry = {version = "^0.10.0", extras = ["refresh"]}
+bioregistry = {version = "^0.10.65", extras = ["refresh"]}
 rdflib = {version = "^6.2.0", extras = ["refresh"]}
 curies = ">=0.5.3"
 tox = "^4.11.3"
+pydantic = "^2.5"
+
 
 [tool.poetry.dev-dependencies]
 pytest = ">=6.2"

src/prefixmaps/data/obo.csv

@@ -157,6 +157,7 @@ obo,OBCS,http://purl.obolibrary.org/obo/OBCS_,canonical
 obo,OBI,http://purl.obolibrary.org/obo/OBI_,canonical
 obo,OBIB,http://purl.obolibrary.org/obo/OBIB_,canonical
 obo,OBO_REL,http://purl.obolibrary.org/obo/OBO_REL_,canonical
+obo,OCCO,http://purl.obolibrary.org/obo/OCCO_,canonical
 obo,OGG,http://purl.obolibrary.org/obo/OGG_,canonical
 obo,OGI,http://purl.obolibrary.org/obo/OGI_,canonical
 obo,OGMS,http://purl.obolibrary.org/obo/OGMS_,canonical

src/prefixmaps/data/prefixcc.csv

@@ -554,6 +554,7 @@ prefixcc,delta,http://www.w3.org/2004/delta#,canonical
 prefixcc,demlab,http://www.demcare.eu/ontologies/demlab.owl#,canonical
 prefixcc,dentsci,https://w3id.org/skgo/dentsci#,canonical
 prefixcc,deo,http://purl.org/spar/deo/,canonical
+prefixcc,deonta,https://deonta.linkedmodel.org/deonta/,canonical
 prefixcc,deps,http://ontologi.es/doap-deps#,canonical
 prefixcc,derecho,http://purl.org/derecho#,canonical
 prefixcc,devuan,https://devuan.net.br/,canonical
@@ -935,7 +936,7 @@ prefixcc,gfo,http://www.onto-med.de/ontologies/gfo.owl#,canonical
 prefixcc,gg,http://www.gemeentegeschiedenis.nl/gg-schema#,canonical
 prefixcc,ggbn,http://data.ggbn.org/schemas/ggbn/terms/,canonical
 prefixcc,ghga,http://w3id.org/ghga/,canonical
-prefixcc,gist,http://ontologies.semanticarts.com/gist/,canonical
+prefixcc,gist,http://ontologies.semanticarts.com/gist#,canonical
 prefixcc,giving,http://ontologi.es/giving#,canonical
 prefixcc,gl,http://schema.geolink.org/,canonical
 prefixcc,gldp,http://www.w3.org/ns/people#,canonical
@@ -1077,6 +1078,7 @@ prefixcc,ifcowl,http://www.buildingsmart-tech.org/ifcOWL/IFC4_ADD2#,canonical
 prefixcc,igeo,http://rdf.insee.fr/def/geo#,canonical
 prefixcc,ignf,http://data.ign.fr/def/ignf#,canonical
 prefixcc,ii,http://sparql.cwrc.ca/ontologies/ii#,canonical
+prefixcc,iig,https://w3id.org/iicongraph/data/,canonical
 prefixcc,iiif,http://iiif.io/api/image/2#,canonical
 prefixcc,ilap,http://data.posccaesar.org/ilap/,canonical
 prefixcc,im,http://imgpedia.dcc.uchile.cl/resource/,canonical
@@ -1563,7 +1565,7 @@ prefixcc,nxs,http://www.neclimateus.org/,canonical
 prefixcc,nyt,http://data.nytimes.com/,canonical
 prefixcc,nytimes,http://data.nytimes.com/elements/,canonical
 prefixcc,oa,http://www.w3.org/ns/oa#,canonical
-prefixcc,oac,http://www.openannotation.org/ns/,canonical
+prefixcc,oac,https://w3id.org/oac#,canonical
 prefixcc,oad,http://lod.xdams.org/reload/oad/,canonical
 prefixcc,oae,http://www.ics.forth.gr/isl/oae/core#,canonical
 prefixcc,oan,http://data.lirmm.fr/ontologies/oan/,canonical

src/prefixmaps/data/w3id.csv

@@ -204,6 +204,7 @@ w3id,cramp-fdp,https://w3id.org/cramp-fdp/,canonical
 w3id,credentials,https://w3id.org/credentials/,canonical
 w3id,credit,https://w3id.org/credit/,canonical
 w3id,cri,https://w3id.org/cri/,canonical
+w3id,cro,https://w3id.org/cro/,canonical
 w3id,cskg,https://w3id.org/cskg/,canonical
 w3id,cso,https://w3id.org/cso/,canonical
 w3id,csolink,https://w3id.org/csolink/,canonical
@@ -490,6 +491,7 @@ w3id,hpont,https://w3id.org/hpont/,canonical
 w3id,hso,https://w3id.org/hso/,canonical
 w3id,hsu-aut,https://w3id.org/hsu-aut/,canonical
 w3id,htad-fdp,https://w3id.org/htad-fdp/,canonical
+w3id,hto,https://w3id.org/hto/,canonical
 w3id,http,https://w3id.org/http/,canonical
 w3id,huml,https://w3id.org/huml/,canonical
 w3id,hydra,https://w3id.org/hydra/,canonical
@@ -515,6 +517,7 @@ w3id,idpo,https://w3id.org/idpo/,canonical
 w3id,idsa,https://w3id.org/idsa/,canonical
 w3id,ieee,https://w3id.org/ieee/,canonical
 w3id,ifc,https://w3id.org/ifc/,canonical
+w3id,ifcc,https://w3id.org/ifcc/,canonical
 w3id,ifcp,https://w3id.org/ifcp/,canonical
 w3id,iicongraph,https://w3id.org/iicongraph/,canonical
 w3id,iliad,https://w3id.org/iliad/,canonical
@@ -684,6 +687,7 @@ w3id,mtv,https://w3id.org/mtv/,canonical
 w3id,MULTI,https://w3id.org/MULTI/,canonical
 w3id,multidimensional-interface,https://w3id.org/multidimensional-interface/,canonical
 w3id,multidimensional-quantity,https://w3id.org/multidimensional-quantity/,canonical
+w3id,mumonut,https://w3id.org/mumonut/,canonical
 w3id,musco,https://w3id.org/musco/,canonical
 w3id,music-annotation,https://w3id.org/music-annotation/,canonical
 w3id,music-circle,https://w3id.org/music-circle/,canonical
@@ -738,9 +742,11 @@ w3id,oebDataFormats,https://w3id.org/oebDataFormats/,canonical
 w3id,oebDatasets,https://w3id.org/oebDatasets/,canonical
 w3id,oerbase,https://w3id.org/oerbase/,canonical
 w3id,ofo,https://w3id.org/ofo/,canonical
+w3id,ogc,https://w3id.org/ogc/,canonical
 w3id,oho,https://w3id.org/oho/,canonical
 w3id,okg,https://w3id.org/okg/,canonical
 w3id,okn,https://w3id.org/okn/,canonical
+w3id,okp4,https://w3id.org/okp4/,canonical
 w3id,olu,https://w3id.org/olu/,canonical
 w3id,omg,https://w3id.org/omg/,canonical
 w3id,omicron,https://w3id.org/omicron/,canonical
@@ -972,6 +978,7 @@ w3id,shp,https://w3id.org/shp/,canonical
 w3id,simpathic,https://w3id.org/simpathic/,canonical
 w3id,simulation,https://w3id.org/simulation/,canonical
 w3id,sip,https://w3id.org/sip/,canonical
+w3id,sirius,https://w3id.org/sirius/,canonical
 w3id,situannotate,https://w3id.org/situannotate/,canonical
 w3id,sketup,https://w3id.org/sketup/,canonical
 w3id,sketx,https://w3id.org/sketx/,canonical

src/prefixmaps/datamodel/context.py

@@ -25,8 +25,7 @@
 PREFIX_RE = re.compile(r"^[\w\.]+$")
 NAMESPACE_RE = re.compile(r"http[s]?://[\w\.\-\/]+[#/_:]$")
 
-logger = logging.getLogger()
-logger.setLevel(logging.INFO)
+logger = logging.getLogger(__name__)
 
 
 class StatusType(Enum):
@@ -71,6 +70,9 @@ class PrefixExpansion:
     status: StatusType
     """Indicates whether the expansion is canonical, a prefix alias, a namespace alias, or both."""
 
+    expansion_source: Optional[str] = None
+    """Indicates the source of the prefix expansion."""
+
     def canonical(self) -> bool:
         """
         True if this is the canonical mapping in both directions.
@@ -153,14 +155,15 @@ def combine(self, context: "Context"):
         :return:
         """
         for pe in context.prefix_expansions:
-            self.add_prefix(pe.prefix, pe.namespace, pe.status)
+            self.add_prefix(pe.prefix, pe.namespace, pe.status, expansion_source=context.name)
 
     def add_prefix(
         self,
         prefix: PREFIX,
         namespace: NAMESPACE,
         status: StatusType = StatusType.canonical,
         preferred: bool = False,
+        expansion_source: Optional[str] = None,
     ):
         """
         Adds a prefix expansion to this context.
@@ -176,6 +179,9 @@ def add_prefix(
         :param namespace: namespace to be added
         :param status: the status of the prefix being added
         :param preferred:
+        :param expansion_source: An optional annotation to be used when merging contexts together.
+            The source will keep track of the original context that a given prefix
+            expansion came from. This is used in :meth:`Context.combine`.
         :return:
         """
         # TODO: check status
@@ -203,6 +209,7 @@ def add_prefix(
                 prefix=prefix,
                 namespace=namespace,
                 status=status,
+                expansion_source=expansion_source,
             )
         )
 

src/prefixmaps/ingest/etl_runner.py

@@ -90,7 +90,7 @@ def run_etl(output_directory: Union[str, Path]) -> None:
     # Write all contexts
     for name, context in contexts.items():
         with output_directory.joinpath(f"{name}.csv").open("w", encoding="UTF-8") as file:
-            context_to_file(context, file)
+            context_to_file(context, file, include_expansion_source=context.name in COMBINED)
 
 
 @click.command

src/prefixmaps/ingest/ingest_bioregistry.py

@@ -64,14 +64,13 @@ def from_bioregistry(upper=False, canonical_idorg=True, filter_dubious=True) ->
         "obofoundry",
         "miriam.legacy" if canonical_idorg else "miriam",
         "default",
-        "bioportal",
         "ols",
         "n2t",
     ]
-    records = bioregistry.get_extended_prefix_map(
+    converter = bioregistry.get_converter(
         uri_prefix_priority=priority, prefix_priority=prefix_priority
     )
-    for record in tqdm(records):
+    for record in tqdm(converter.records):
         if record.prefix in SKIP:
             continue
         if filter_dubious and not NAMESPACE_RE.match(record.uri_prefix):
@@ -82,7 +81,6 @@ def from_bioregistry(upper=False, canonical_idorg=True, filter_dubious=True) ->
         if record.prefix not in PROBLEMATIC_CURIE_PREFIX_SYNONYMS_RECORDS:
             for s in record.prefix_synonyms:
                 context.add_prefix(s, record.uri_prefix, preferred=preferred)
-        # TODO future, add URI prefix synonyms
-        # for s in record.uri_prefix_synonyms:
-        #     context.add_prefix(record.prefix, s, status=StatusType.namespace_alias, preferred=preferred)
+            for s in record.uri_prefix_synonyms:
+                context.add_prefix(record.prefix, s, preferred=preferred)
     return context

src/prefixmaps/io/writer.py

@@ -15,17 +15,27 @@ def _key(pe: PrefixExpansion):
     return pe.prefix.casefold(), STATUS_TYPE_ORDER[pe.status]
 
 
-def context_to_file(context: Context, file: TextIO) -> None:
+def context_to_file(
+    context: Context, file: TextIO, *, include_expansion_source: bool = False
+) -> None:
     """
     Writes a context to a file
 
     :param context:
     :param file:
+    :param include_expansion_source: If true, include a "source" column. This is useful for
+        writing merged contexts since it says the highest priority simple context
+        from which the row corresponding to a :class:`PrefixExpansion` came.
     :return:
     """
-    writer = DictWriter(file, fieldnames=["context", "prefix", "namespace", "status"])
+    field_names = ["context", "prefix", "namespace", "status"]
+    if include_expansion_source:
+        field_names.append("expansion_source")
+    writer = DictWriter(file, fieldnames=field_names)
     writer.writeheader()
     for pe in sorted(context.prefix_expansions, key=_key):
         row = vars(pe)
         row["status"] = pe.status.value
+        if not include_expansion_source:
+            row.pop("expansion_source", None)
         writer.writerow(row)