test(ocr): add portable vnext real-paper comparison harness

scripts/dev/compare_figure_inventory_legacy_vs_vnext.py

@@ -31,6 +31,14 @@ def compare_inventories(legacy: dict[str, object], vnext: dict[str, object]) ->
         ),
     }
 
+def compare_blocks_file(blocks_path: Path) -> dict[str, object]:
+    blocks = [json.loads(line) for line in blocks_path.read_text(encoding="utf-8").splitlines() if line.strip()]
+    legacy = build_figure_inventory_legacy(blocks)
+    vnext = build_figure_inventory_vnext(blocks)
+    diff = compare_inventories(legacy, vnext)
+    diff["paper"] = blocks_path.parent.name
+    return diff
+
 
 def main(blocks_path: str) -> int:
     blocks = [json.loads(line) for line in Path(blocks_path).read_text(encoding="utf-8").splitlines() if line.strip()]

tests/test_ocr_figure_vnext_real_papers.py

@@ -0,0 +1,14 @@
+from pathlib import Path
+
+from scripts.dev.compare_figure_inventory_legacy_vs_vnext import compare_blocks_file
+
+
+def test_real_paper_same_page_milestone_reports_diff_shape():
+    blocks_path = Path("tests/fixtures/ocr_vnext_real_papers/2HEUD5P9/blocks.structured.jsonl")
+    diff = compare_blocks_file(blocks_path)
+
+    assert diff["paper"] == "2HEUD5P9"
+    assert "legacy_matched_count" in diff
+    assert "vnext_matched_count" in diff
+    assert "legacy_consumed_block_ids" in diff
+    assert "vnext_consumed_block_ids" in diff