From 1c59404abb1894ad9f3b4071a78daf4004482980 Mon Sep 17 00:00:00 2001
From: Alex Nelson <alexander.nelson@nist.gov>
Date: Fri, 31 May 2024 15:53:21 -0400
Subject: [PATCH] Test for IRIs that share UUIDs

This is part of implementing CASE-Examples-QC PR 54.

No effects were observed on Make-managed files.

References:
* https://github.com/ajnelson-nist/CASE-Examples-QC/pull/54

Signed-off-by: Alex Nelson <alexander.nelson@nist.gov>
---
 examples/postvisit.mk                         | 12 ++++
 .../test_kb_casework_github_io_examples.py    | 64 +++++++++++++++++++
 2 files changed, 76 insertions(+)
 create mode 100644 examples/test_kb_casework_github_io_examples.py

diff --git a/examples/postvisit.mk b/examples/postvisit.mk
index f0f5c6cc..0d4a9b08 100644
--- a/examples/postvisit.mk
+++ b/examples/postvisit.mk
@@ -30,6 +30,9 @@ all_jsonld := $(foreach illustration_dir,$(illustration_dirs),$(illustration_dir
 all: \
   kb.ttl
 
+.PHONY: \
+  check-pytest
+
 all-drafting.ttl: \
   $(all_drafting_ttl)
 	source $(top_srcdir)/venv/bin/activate \
@@ -40,7 +43,16 @@ all-drafting.ttl: \
 	mv _$@ $@
 
 check: \
+  check-pytest
+
+check-pytest: \
   kb.ttl
+	source $(top_srcdir)/venv/bin/activate \
+	  && pytest \
+	    --ignore urgent_evidence \
+	    --log-level=DEBUG \
+	    --verbose \
+	    --verbose
 
 clean:
 	@rm -f \
diff --git a/examples/test_kb_casework_github_io_examples.py b/examples/test_kb_casework_github_io_examples.py
new file mode 100644
index 00000000..c8d02b05
--- /dev/null
+++ b/examples/test_kb_casework_github_io_examples.py
@@ -0,0 +1,64 @@
+#!/usr/bin/env python3
+
+# Portions of this file contributed by NIST are governed by the
+# following statement:
+#
+# This software was developed at the National Institute of Standards
+# and Technology by employees of the Federal Government in the course
+# of their official duties. Pursuant to Title 17 Section 105 of the
+# United States Code, this software is not subject to copyright
+# protection within the United States. NIST assumes no responsibility
+# whatsoever for its use by other parties, and makes no guarantees,
+# expressed or implied, about its quality, reliability, or any other
+# characteristic.
+#
+# We would appreciate acknowledgement if the software is used.
+
+import logging
+from collections import defaultdict
+from pathlib import Path
+from pprint import pformat
+from typing import DefaultDict, Dict, Set
+from uuid import UUID
+
+from rdflib import Graph, URIRef
+
+srcdir = Path(__file__).parent
+
+
+def test_uuid_unique_usage_casework_github_io() -> None:
+    """
+    This test confirms that if two node IRIs end with the same UUID, then the IRI matches.
+    This test is likely to be copied and adjusted between several example repositories.
+    """
+    uuid_to_urirefs: DefaultDict[UUID, Set[URIRef]] = defaultdict(set)
+    graph = Graph()
+    graph.parse(srcdir / "kb.ttl")
+
+    def _ingest(n_thing: URIRef) -> None:
+        thing_iri = str(n_thing)
+        if len(thing_iri) < 40:
+            # Not long enough to contain scheme, colon, and UUID.
+            return
+        try:
+            thing_uuid = UUID(thing_iri[-36:])
+        except ValueError:
+            return
+        uuid_to_urirefs[thing_uuid].add(n_thing)
+
+    for triple in graph.triples((None, None, None)):
+        if isinstance(triple[0], URIRef):
+            _ingest(triple[0])
+        if isinstance(triple[2], URIRef):
+            _ingest(triple[2])
+
+    computed: Dict[str, Set[str]] = dict()
+    for _uuid in uuid_to_urirefs:
+        if len(uuid_to_urirefs[_uuid]) > 1:
+            computed[str(_uuid)] = {str(x) for x in uuid_to_urirefs[_uuid]}
+
+    try:
+        assert len(computed) == 0
+    except AssertionError:
+        logging.debug(pformat(computed))
+        raise