Add Phase 2 end-to-end integration test for native SPDX 3 constructs

CHANGELOG.md

@@ -22,7 +22,7 @@ and this project adheres to
 
 ### Added
 
-- Native-first provenance backfills (Phase 2):
+- Native-first provenance backfills (native SPDX backfill):
   - `hasConcludedLicense` vs. `hasDeclaredLicense` separation
     for detected vs. author-asserted licenses.
   - Native `ExternalIdentifier` (DOI) and `ExternalRef`

src/pitloom/assemble/spdx3/ai.py

@@ -203,7 +203,7 @@ def _add_base_model_lineage(
     ai_model: AiModelMetadata,
     ctx: _LineageContext,
 ) -> None:
-    """Add native Relationship (descendantOf) linking ai_pkg to its base model (N5)."""
+    """Add native descendantOf Relationship linking ai_pkg to its base model."""
     base_model_id = ai_model.base_model or ai_model.extra_data.get("hf.base_model")
     if not base_model_id:
         return

src/pitloom/assemble/spdx3/fragments.py

@@ -50,7 +50,7 @@
 #: genuinely *distinct* id into the survivor ("these two different ids are the
 #: same bytes"), which SPDX cannot express and which the merge would otherwise
 #: discard. A same-id registry match (dropped id == survivor id) carries no such
-#: fact -- its only content is the fragment origin, which belongs to the Phase-2
+#: fact -- its only content is the fragment origin, which belongs to the native
 #: ``SpdxDocument.imports`` native anchor, not here. Agent/Tool structural dedup
 #: (every fragment mints its own "Pitloom") is likewise excluded.
 _UnificationEvents = dict[str, dict[str, dict[str, set[str]]]]
@@ -475,7 +475,7 @@ def _merge_fragment_set(
         if by_id is not None:
             # Same-id (registry) match: the fragment reused an existing id, so
             # nothing distinct is folded. Its only fact is the fragment origin,
-            # which is Phase-2 SpdxDocument.imports territory -- not annotated
+            # which is SpdxDocument.imports territory -- not annotated
             # here (see _UnificationEvents). Properties are still merged.
             _merge_properties(_as_element(by_id), _as_element(obj))
             remap[obj] = require_spdx_id(_as_element(by_id))
@@ -598,7 +598,7 @@ def _add_fragment_imports(
     fragment_imports: list[spdx3.ExternalMap],
 ) -> None:
     """Populate ``main_doc.import_`` with ``ExternalMap`` entries for merged
-    fragment documents (N1)."""
+    fragment documents."""
     if not fragment_imports:
         return
     existing_imports = list(main_doc.import_ or [])

src/pitloom/assemble/spdx3/provenance.py

@@ -304,7 +304,7 @@ def build_unification_annotation(
     the survivor *subject_spdx_id* (A1).
 
     SPDX has no native home for this: the merged-away ids vanish from the graph
-    and ``SpdxDocument.imports`` (a Phase-2 native anchor, see the design doc)
+    and ``SpdxDocument.imports`` (a native anchor, see the design doc)
     can only say an element came from a fragment, not the matching *criterion*.
 
     Args:

tests/test_fragments.py

@@ -990,7 +990,8 @@ def test_unification_annotation_records_sha256_merge() -> None:
 
 def test_merge_fragments_populates_spdx_document_imports(tmp_path: Path) -> None:
     """merge_fragments() must populate main_doc.import_ with ExternalMap
-    entries naming each merged fragment's SpdxDocument spdxId and location hint (N1).
+    entries naming each merged fragment's SpdxDocument spdxId and location hint
+    (fragment origin).
     """
     frag_namespace = "https://spdx.org/spdxdocs/fragment-import-test"
     envelope_fragment = {

tests/test_generator.py

@@ -1388,7 +1388,7 @@ def test_build_model_without_license() -> None:
 
 def test_build_model_external_identifiers() -> None:
     """build_model() must emit ExternalIdentifier for DOI and ExternalRef for
-    arXiv paper IDs and model page URLs (N4).
+    arXiv paper IDs and model page URLs (external identifiers).
     """
     model = AiModelMetadata(
         format_info=AiModelFormatInfo(model_format=AiModelFormat.SAFETENSORS),
@@ -1440,7 +1440,8 @@ def test_build_model_external_identifiers() -> None:
 
 def test_build_model_with_dataset_creator() -> None:
     """build_model() for a model linked to a dataset with creator metadata
-    must emit an Agent element and a publishedBy Relationship (N6).
+    must emit an Agent element and a publishedBy Relationship
+    (dataset creator attribution).
     """
     ds_meta = DatasetMetadata(name="squad", creator="Stanford NLP")
     ds_ref = DatasetReference(role="trainedOn", metadata=ds_meta)
@@ -1619,7 +1620,8 @@ def test_generate_deployed_sbom_mocked_pipdeptree(
 
 def test_build_model_base_model_lineage() -> None:
     """build_model() must emit a stub base model ai_AIPackage and a descendantOf
-    Relationship when base_model and base_model_relation are present (N5).
+    Relationship when base_model and base_model_relation are present
+    (base-model lineage).
     """
     meta = AiModelMetadata(
         name="my-finetuned-model",