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

fix: prevent frontmatter_noise rescue in page footer zone

Browse source
This commit is contained in:
Research Assistant 2026-06-07 22:31:05 +08:00
parent 463cd4d7b1
commit d7974867cc
1 changed files with 4 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
paperforge/worker/ocr_document.py
View file

@ -1164,6 +1164,10 @@ def rescue_roles_with_document_context(
# --- Rule 1: frontmatter_noise → body_paragraph (body section + body font)
if block.get("role") == "frontmatter_noise":
page = block.get("page", 1) or 1
bbox = block.get("bbox") or block.get("block_bbox") or [0, 0, 0, 0]
page_h = block.get("page_height") or 1700
if len(bbox) >= 4 and bbox[1] > page_h * 0.85:
continue
if body_end_page is not None and page <= body_end_page:
bp = extract_block_span_profile(block)
if bp: