From 1a81817d7fc248754df84fe9f1f9ff8b0546016d Mon Sep 17 00:00:00 2001
From: LLLin000 <809867916@qq.com>
Date: Sat, 4 Jul 2026 16:06:06 +0800
Subject: [PATCH] test: add OCR pipeline v3 parity gate

---
 tests/test_ocr_pipeline_v3.py | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/tests/test_ocr_pipeline_v3.py b/tests/test_ocr_pipeline_v3.py
index 3c36ef58..f5319ebf 100644
--- a/tests/test_ocr_pipeline_v3.py
+++ b/tests/test_ocr_pipeline_v3.py
@@ -179,3 +179,24 @@ def test_post_match_normalize_commits_shadow_role_back_to_public_role(monkeypatc
     assert out_rows[0]["role_candidate"] == "figure_caption_candidate"
     assert out_rows[0]["role_source"] == "shadow_post_match"
     assert doc is not None
+
+
+
+def test_build_structured_blocks_legacy_default_still_matches_seed_contract() -> None:
+    from paperforge.worker.ocr_blocks import build_structured_blocks
+
+    raw_blocks = [
+        {
+            "paper_id": "test_paper",
+            "block_id": "r1",
+            "page": 1,
+            "raw_label": "text",
+            "text": "Minimal body text.",
+            "bbox": [100, 100, 420, 140],
+        }
+    ]
+
+    rows, _ = build_structured_blocks(raw_blocks)
+
+    assert rows[0]["role"]
+    assert rows[0]["seed_role"]
\ No newline at end of file