feat(runtime): implement single-article consolidation runtime and modularize codebase

2026-08-24 00:14:07 -03:00
parent e1e0be1353
commit 23de7d8fe7
176 changed files with 266754 additions and 10179 deletions
@@ -0,0 +1,48 @@
+"""Contract tests for hygiene-response.schema.json."""
+
+from __future__ import annotations
+
+import jsonschema
+
+from src.runtime.core.config import create_schema_registry, load_schema
+
+
+def test_hygiene_response_schema_valid():
+    schema = load_schema("hygiene-response.schema.json")
+    registry = create_schema_registry()
+    validator = jsonschema.Draft202012Validator(schema, registry=registry)
+
+    valid_response = {
+        "title_candidate_id": "title_meta",
+        "subtitle_candidate_id": "subtitle_meta",
+        "author_candidate_id": "author_trafilatura",
+        "kept_block_ids": ["trafilatura_blk_001", "trafilatura_blk_002"],
+        "kept_link_ids": [],
+        "kept_image_ids": [],
+        "repairs": [
+            {
+                "target_candidate_id": "trafilatura_blk_001",
+                "original_fragment": "River Plate empatÃ³",
+                "replacement_fragment": "River Plate empató",
+                "category": "encoding",
+                "rationale": "Fix moji-bake encoding artifact.",
+            }
+        ],
+        "removal_reasons": {"trafilatura_blk_003": "advertisement"},
+    }
+
+    errors = list(validator.iter_errors(valid_response))
+    assert len(errors) == 0, f"Schema errors: {[e.message for e in errors]}"
+
+
+def test_hygiene_response_schema_missing_required():
+    schema = load_schema("hygiene-response.schema.json")
+    registry = create_schema_registry()
+    validator = jsonschema.Draft202012Validator(schema, registry=registry)
+
+    invalid_response = {
+        "kept_block_ids": ["blk_01"]
+        # Missing title_candidate_id, repairs, etc.
+    }
+    errors = list(validator.iter_errors(invalid_response))
+    assert len(errors) > 0