Add safe Vcore wowdiag and wowsrc imports with original-data provenance

tests/profiles/vcore/test_real_package.py

@@ -0,0 +1,40 @@
+"""Opt-in full-archive regression, without machine-specific paths or binary fixtures."""
+import hashlib
+import json
+import os
+from pathlib import Path
+
+import pytest
+
+from viano_bug_analysis.case import CaseBuilder
+from viano_bug_analysis.lifecycle import CheckpointStore, Workspace
+from viano_bug_analysis.package import PackageReader, PackageValidator
+from viano_bug_analysis.profiles.vcore import ArchiveReader, VcoreImporter
+
+
+@pytest.mark.skipif(not os.environ.get("VBA_WOWDIAG_SAMPLE") or not os.environ.get("VBA_WOWSRC_SAMPLE"),
+                    reason="Set VBA_WOWDIAG_SAMPLE and VBA_WOWSRC_SAMPLE for the BUG-20 full archive regression")
+def test_full_bug20_package_pair(tmp_path):
+    diag, src = Path(os.environ["VBA_WOWDIAG_SAMPLE"]), Path(os.environ["VBA_WOWSRC_SAMPLE"])
+    original_hashes = [hashlib.sha256(path.read_bytes()).hexdigest() for path in (diag, src)]
+    package = tmp_path / "anything.bin"
+    VcoreImporter().create(diag, package, package_id="regression-package", case_id="regression-case", wowsrc=src)
+    store = CheckpointStore(Workspace(tmp_path / "service"))
+    store.intake(package)
+    result = CaseBuilder(store).build("regression-case", "regression-package")
+    assert PackageValidator().validate(result.package).valid
+    with PackageReader(result.package) as reader:
+        case = json.loads(reader.read_bytes(result.case_ref))
+        assert len(case["human_observations"]["observations"]) == 3
+        assert case["expected_behavior"]["completeness"] == "missing"
+        assert case["human_observations"]["tester_hypotheses"] == []
+        assert len(case["database_context"]["refs"]) == 103
+        assert len(case["source_context"]["refs"]) == 93
+        for input_path in (diag, src):
+            with ArchiveReader(input_path) as source:
+                for member in source.members:
+                    matching = [path for path in reader.files if path.endswith("/members/" + member)]
+                    assert len(matching) == 1
+                    assert reader.read_bytes(matching[0]) == source.read_member(member)
+    assert CaseBuilder(store).build("regression-case", "regression-package").reused
+    assert [hashlib.sha256(path.read_bytes()).hexdigest() for path in (diag, src)] == original_hashes