get a report of envo terms with ids in the range of nmdc or nmdc contributors

.gitignore

@@ -1,4 +1,6 @@
 src/ontology/nmdco-redundant.ttl
+local/
+**/__pycache__/
 
 .DS_Store
 .idea/

envo_id_ranges_report.tsv

@@ -0,0 +1,27 @@
+range	owner	min	max
+1	Norman Morrison	1	999999
+10	ENVO-P, E-NumberOf-E	9400000	9499999
+11	Kai Blumberg pattern generated terms	3100001	3200000
+13	chemical_concentration.yaml yaml design pattern	3200001	3300000
+14	ebi_biomes.csv robot design pattern	3300001	3400000
+15	Ruth Duerr	3400001	3500000
+16	Anne Thessen	3500001	3501000
+17	Anton Van de Putte	3501001	3501100
+2	Pier Luigi Buttigieg	1000000	1999999
+20	Raissa Meyer	3520000	3529999
+21	Brandon Whitehead	6000000	6100000
+22	Jimena Linares	6100001	6105000
+23	Mei-Chen Liu	6105001	6105100
+24	Isabella Maria Wilkie	6105101	6105200
+25	National Microbiome Data Collaborative	3600000	3600099
+26	Agronomy Ontology	6105201	6105499
+27	ANZ Soil and Land survey	5000000	5100000
+28	Alicia Clum	3600100	3604999
+29	Mark Andrew Miller	3605000	3609999
+3	Chris Mungall	2000000	2999999
+4	TermGenie	8000000	8999999
+5	ENVO-P, E-A-L	9000000	9099999
+6	ENVO-P, E-Q-L	9100000	9199999
+7	ENVO-P, E-A	9200000	9299999
+8	Kai Blumberg	3000000	3100000
+9	ENVO-P, E-Content-E	9300000	9399999

maintenance.Makefile

@@ -0,0 +1,21 @@
+RUN=poetry run
+
+local/envo-idranges.owl.omn:
+	@echo "Downloading..."
+ifeq ($(shell command -v wget 2> /dev/null),)
+	@echo "wget is not installed, trying with curl..."
+	@curl -o $@ https://raw.githubusercontent.com/EnvironmentOntology/envo/master/src/envo/envo-idranges.owl
+else
+	@echo "Downloading with wget..."
+	@wget -O $@ https://raw.githubusercontent.com/EnvironmentOntology/envo/master/src/envo/envo-idranges.owl
+endif
+
+local/envo-idranges.owl.ttl: local/envo-idranges.owl.omn
+	@echo "Converting..."
+	@robot convert --input $< --output $@
+
+envo_id_ranges_report.tsv: local/envo-idranges.owl.ttl
+	@echo "Generating report..."
+	$(RUN) report-id-ranges \
+		--id-ranges-ttl $< \
+		--output $@

nmdc_ontology/report_id_ranges.py

@@ -0,0 +1,59 @@
+import click
+from rdflib import Graph, Namespace
+import pandas as pd
+
+
+@click.command()
+@click.option("--id-ranges-ttl", "-i", default="local/envo-idranges.owl.ttl", help="Input file path")
+@click.option("--output", "-o", default="envo_id_ranges_report.tsv", help="Output file path")
+def generate_id_ranges(id_ranges_ttl, output):
+    # Load the Turtle content into an RDF graph
+    g = Graph()
+    g.parse(id_ranges_ttl, format="turtle")
+
+    # Define namespaces
+    obo = Namespace("http://purl.obolibrary.org/obo/")
+    ro = Namespace("http://purl.obolibrary.org/obo/ro/")
+    iao = Namespace("http://purl.obolibrary.org/obo/IAO_")
+    rdf = Namespace("http://www.w3.org/1999/02/22-rdf-syntax-ns#")
+    xsd = Namespace("http://www.w3.org/2001/XMLSchema#")
+    owl = Namespace("http://www.w3.org/2002/07/owl#")
+    rdfs = Namespace("http://www.w3.org/2000/01/rdf-schema#")
+
+    # Construct SPARQL query string
+    query = """
+        PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
+        PREFIX owl: <http://www.w3.org/2002/07/owl#>
+        PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
+        PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
+        PREFIX obo: <http://purl.obolibrary.org/obo/>
+        SELECT ?range ?owner ?min ?max
+        WHERE {
+            ?range a rdfs:Datatype ;
+                   owl:equivalentClass ?ec ;
+                   obo:IAO_0000597 ?owner .
+            ?ec owl:withRestrictions ?restrictions .
+            ?restrictions rdf:first ?first ;
+                          rdf:rest ?rest .
+            ?first xsd:minInclusive ?min .
+            ?rest rdf:first ?rest_first .
+            ?rest_first xsd:maxInclusive ?max .
+        }
+    """
+
+    # Execute the SPARQL query and convert results to DataFrame
+    results = g.query(query)
+    data = [(str(row.range), str(row.owner), str(row.min), str(row.max)) for row in results]
+    data = [(str(row.range).replace("http://purl.obolibrary.org/obo/ro/idrange/", ""), str(row.owner), str(row.min),
+             str(row.max)) for row in results]
+
+    df = pd.DataFrame(data, columns=['range', 'owner', 'min', 'max'])
+
+    # Save DataFrame as TSV
+    df.to_csv(output, sep="\t", index=False)
+
+    click.echo(f"ID ranges saved to {output}")
+
+
+if __name__ == "__main__":
+    generate_id_ranges()

pyproject.toml

@@ -12,11 +12,13 @@ pandas = "^2.2.0"
 requests = "^2.31.0"
 pyarrow = "^15.0.0"
 click = "^8.1.7"
+rdflib = "^7.0.0"
 
 
 [build-system]
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"
 
 [tool.poetry.scripts]
-report-instantiated-traids = "nmdc_ontology.report_instantiated_traids:main"
+report-instantiated-traids = "nmdc_ontology.report_instantiated_traids:main"
+report-id-ranges = "nmdc_ontology.report_id_ranges:generate_id_ranges"