obsidian-plugin/lllin000_PaperForge
1
0
Fork 0
mirror of https://github.com/lllin000/PaperForge.git synced 2026-07-22 06:50:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

test: add OCR pipeline v3 parity gate

Browse source
This commit is contained in:
LLLin000 2026-07-04 16:06:06 +08:00
parent cb685f73d0
commit 1a81817d7f
1 changed files with 21 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

21
tests/test_ocr_pipeline_v3.py
View file

@ -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"]