Establish AAISA research foundation

tests/test_scanner.py

@@ -0,0 +1,51 @@
+import json
+from pathlib import Path
+import tempfile
+import unittest
+
+from aaisa.config import Config
+from aaisa.artifacts import classify
+from aaisa.models import Severity
+from aaisa.reporters import json_report, sarif_report
+from aaisa.scanner import Scanner
+
+
+class ScannerTests(unittest.TestCase):
+    def test_threat_model_is_not_misclassified_as_model_metadata(self) -> None:
+        self.assertEqual(classify(Path("THREAT_MODEL.md")), "document")
+        self.assertEqual(classify(Path("model-card.yaml")), "model-metadata")
+
+    def test_scan_hashes_artifacts_and_skips_symlinks(self) -> None:
+        with tempfile.TemporaryDirectory() as directory:
+            root = Path(directory)
+            (root / "safe.txt").write_text("ordinary content\n", encoding="utf-8")
+            try:
+                (root / "outside-link").symlink_to(Path(directory).parent)
+            except OSError:
+                pass
+            report = Scanner(Config(minimum_severity=Severity.INFO)).scan(root)
+            self.assertEqual([item["path"] for item in report.artifacts], ["safe.txt"])
+            self.assertEqual(len(report.artifacts[0]["sha256"]), 64)
+
+    def test_oversize_artifact_is_an_error(self) -> None:
+        with tempfile.TemporaryDirectory() as directory:
+            path = Path(directory) / "large.txt"
+            path.write_text("x" * 20, encoding="utf-8")
+            report = Scanner(Config(max_file_bytes=10)).scan(Path(directory))
+            self.assertEqual(report.artifacts, [])
+            self.assertEqual(report.errors[0]["path"], "large.txt")
+
+    def test_reports_are_machine_readable(self) -> None:
+        with tempfile.TemporaryDirectory() as directory:
+            path = Path(directory) / "requirements.txt"
+            path.write_text("requests>=2\n", encoding="utf-8")
+            report = Scanner().scan(Path(directory))
+            json_payload = json.loads(json_report(report))
+            sarif_payload = json.loads(sarif_report(report))
+            self.assertEqual(json_payload["schema_version"], "1.0.0")
+            self.assertEqual(sarif_payload["version"], "2.1.0")
+            self.assertEqual(sarif_payload["runs"][0]["results"][0]["ruleId"], "AAISA-DEPENDENCY-001")
+
+
+if __name__ == "__main__":
+    unittest.main()