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 +1,59 @@
+"""Unit tests for Markdown renderer covering scenarios OUT-002 to OUT-010."""
+
+import yaml
+
+from src.runtime.candidate.models import CandidateObject
+from src.runtime.storage.markdown_renderer import render_canonical_markdown
+
+
+def test_render_canonical_markdown_with_front_matter():
+    blocks = [
+        CandidateObject(
+            id="blk_01",
+            type="heading",
+            text="Primeiro Bloco",
+            extractor="trafilatura",
+            position=1,
+            level=2,
+        ),
+        CandidateObject(
+            id="blk_02",
+            type="paragraph",
+            text="Este é o parágrafo editorial.",
+            extractor="trafilatura",
+            position=2,
+        ),
+        CandidateObject(
+            id="blk_03", type="list_item", text="Item de lista", extractor="trafilatura", position=3
+        ),
+    ]
+
+    rendered = render_canonical_markdown(
+        title="Título do Artigo",
+        subtitle="Subtítulo informativo",
+        fingerprint="a" * 64,
+        source_url="https://example.com/art",
+        published_date="2026-08-20T10:00:00Z",
+        language="pt",
+        sentiment="positive",
+        tags=["economia", "petrobras", "brasil"],
+        ecp_target_id="Q123",
+        ecp_target_name="Petrobras",
+        body_blocks=blocks,
+    )
+
+    assert rendered.startswith("---\n")
+    assert "# Título do Artigo" in rendered
+    assert "*Subtítulo informativo*" in rendered
+    assert "## Primeiro Bloco" in rendered
+    assert "Este é o parágrafo editorial." in rendered
+    assert "- Item de lista" in rendered
+
+    # Verify front matter parses as valid YAML
+    parts = rendered.split("---\n")
+    front_matter_raw = parts[1]
+    parsed_fm = yaml.safe_load(front_matter_raw)
+    assert parsed_fm["title"] == "Título do Artigo"
+    assert parsed_fm["fingerprint"] == "a" * 64
+    assert parsed_fm["sentiment"] == "positive"
+    assert parsed_fm["tags"] == ["economia", "petrobras", "brasil"]