feat(okf): add okf_validate; harden YAML parser for block lists + folded scalars

Verified conformant against Google reference bundles (crypto_bitcoin, ga4, stackoverflow).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

custom-skills/97-ourdigital-okf/code/scripts/tests/test_okf_common.py

@@ -24,6 +24,21 @@ class TestFrontmatter(unittest.TestCase):
     def test_empty_list(self):
         self.assertEqual(parse_yaml_subset("tags: []")["tags"], [])
 
+    def test_block_list(self):
+        raw = "type: BigQuery Dataset\ntags:\n- cryptocurrency\n- bitcoin\n- public data\ntimestamp: '2026-05-28T22:44:47+00:00'"
+        meta = parse_yaml_subset(raw)
+        self.assertEqual(meta["tags"], ["cryptocurrency", "bitcoin", "public data"])
+        self.assertEqual(meta["timestamp"], "2026-05-28T22:44:47+00:00")
+
+    def test_folded_multiline_scalar(self):
+        raw = "description: This dataset contains a complete history of the Bitcoin\n  blockchain and updates every 10 minutes.\ntype: BigQuery Dataset"
+        meta = parse_yaml_subset(raw)
+        self.assertEqual(
+            meta["description"],
+            "This dataset contains a complete history of the Bitcoin blockchain and updates every 10 minutes.",
+        )
+        self.assertEqual(meta["type"], "BigQuery Dataset")
+
     def test_no_frontmatter(self):
         meta, body = parse_frontmatter("# Just markdown\n")
         self.assertIsNone(meta)

custom-skills/97-ourdigital-okf/code/scripts/tests/test_okf_validate.py

@@ -0,0 +1,64 @@
+import sys, tempfile, unittest
+from pathlib import Path
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+from okf_validate import validate_bundle
+
+FIX = Path(__file__).resolve().parent / "fixtures" / "mini_bundle"
+GOOGLE = Path.home() / "Documents/reference-library/open-knowledge-format/okf/bundles"
+
+
+def write_bundle(root, files):
+    for rel, content in files.items():
+        p = Path(root) / rel
+        p.parent.mkdir(parents=True, exist_ok=True)
+        p.write_text(content, encoding="utf-8")
+
+
+class TestValidate(unittest.TestCase):
+    def test_mini_fixture_conformant(self):
+        report = validate_bundle(FIX)
+        self.assertTrue(report["conformant"], report["errors"])
+        self.assertGreaterEqual(report["concepts"], 3)
+
+    def test_missing_type_is_error(self):
+        with tempfile.TemporaryDirectory() as d:
+            write_bundle(d, {"tables/x.md": "---\ntitle: X\n---\nbody"})
+            report = validate_bundle(d)
+            self.assertFalse(report["conformant"])
+            self.assertTrue(any(e["rule"] == "type" for e in report["errors"]))
+
+    def test_missing_frontmatter_is_error(self):
+        with tempfile.TemporaryDirectory() as d:
+            write_bundle(d, {"tables/x.md": "# no frontmatter\n"})
+            self.assertFalse(validate_bundle(d)["conformant"])
+
+    def test_reserved_files_not_required_to_have_type(self):
+        with tempfile.TemporaryDirectory() as d:
+            write_bundle(d, {"index.md": "# Index\n* [x](/tables/x.md)\n",
+                             "tables/x.md": "---\ntype: T\n---\nb"})
+            self.assertTrue(validate_bundle(d)["conformant"])
+
+    def test_broken_link_is_warning_not_error(self):
+        with tempfile.TemporaryDirectory() as d:
+            write_bundle(d, {"tables/x.md": "---\ntype: T\n---\nSee [y](/tables/y.md)."})
+            report = validate_bundle(d)
+            self.assertTrue(report["conformant"])
+            self.assertTrue(any(w["rule"] == "broken_link" for w in report["warnings"]))
+
+
+class TestGoogleBundles(unittest.TestCase):
+    @unittest.skipUnless(GOOGLE.exists(), "Google reference bundles not present")
+    def test_google_sample_bundles_conformant(self):
+        for name in ("crypto_bitcoin", "ga4", "stackoverflow"):
+            bundle = GOOGLE / name
+            if not bundle.exists():
+                continue
+            report = validate_bundle(bundle)
+            self.assertTrue(
+                report["conformant"],
+                "%s non-conformant; first errors: %s" % (name, report["errors"][:3]),
+            )
+
+
+if __name__ == "__main__":
+    unittest.main()