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 failing pair-group figure inventory case

Browse source
This commit is contained in:
Research Assistant 2026-06-15 15:14:14 +08:00
parent ab81677419
commit 416232d638
1 changed files with 29 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

29
tests/test_ocr_figures.py
View file

@ -1952,3 +1952,32 @@ def test_reader_figures_never_include_empty_visual_groups() -> None:
assert vg, (
f"Reader figure {figure.get('reader_figure_id')} has empty visual_groups: {figure}"
)
# === group-first matching (Task 1: Red test) ===
def test_group_first_matching_prefers_same_row_pair_over_single_asset() -> None:
from paperforge.worker.ocr_figures import build_figure_inventory
blocks = [
{
"block_id": 1,
"role": "figure_caption",
"text": "Fig. 2 A and B, MRI and gross anatomic correlation.",
"page": 3,
"bbox": [80, 120, 420, 210],
"marker_signature": {"type": "figure_number", "number": 2},
"zone": "display_zone",
"style_family": "legend_like",
},
{"block_id": 2, "role": "media_asset", "raw_label": "image", "page": 3, "bbox": [450, 120, 780, 520]},
{"block_id": 3, "role": "media_asset", "raw_label": "image", "page": 3, "bbox": [805, 120, 1130, 520]},
]
inventory = build_figure_inventory(blocks, page_width=1200)
matched = inventory["matched_figures"]
assert len(matched) == 1
assert matched[0]["figure_number"] == 2
assert [a["block_id"] for a in matched[0]["matched_assets"]] == [2, 3]