obsidian-plugin/lllin000_PaperForge
1
0
Fork 0
mirror of https://github.com/lllin000/PaperForge.git synced 2026-07-22 17:00:23 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: render section_heading with Markdown heading prefix

Browse source
This commit is contained in:
Research Assistant 2026-06-07 12:53:04 +08:00
parent 088fb4144d
commit ee5cd0df4e
2 changed files with 20 additions and 13 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
paperforge/worker/ocr_render.py
View file

@ -843,17 +843,15 @@ def render_fulltext_markdown(
if role == "backmatter_boundary_heading" or role == "backmatter_heading" or role == "reference_heading":
lines.append(f"## {text}")
lines.append("")
elif role == "section_heading":
if text.strip().lower() in FRONTMATTER_NOISE:
continue
if _is_bogus_heading(text):
if text:
lines.append(text)
lines.append("")
else:
lines.append(f"## {text}")
lines.append("")
elif role == "subsection_heading" or role == "sub_subsection_heading":
elif role in ("subsection_heading", "sub_subsection_heading", "section_heading"):
if role == "section_heading":
if text.strip().lower() in FRONTMATTER_NOISE:
continue
if _is_bogus_heading(text):
if text:
lines.append(text)
lines.append("")
continue
lines.append(f"### {text}")
lines.append("")
elif role in ("backmatter_body", "tail_candidate_body", "body_paragraph"):

13
tests/test_ocr_render_stabilization.py
View file

@ -315,7 +315,7 @@ def test_stabilize_heading_sanity_allows_valid_short_heading() -> None:
table_inventory={},
)
assert "## 1 Introduction" in md
assert "### 1 Introduction" in md
def test_stabilize_heading_sanity_downgrades_verb_heavy_heading() -> None:
@ -374,7 +374,7 @@ def test_stabilize_heading_sanity_allows_verb_short_heading() -> None:
table_inventory={},
)
assert "## Results are shown" in md
assert "### Results are shown" in md
def test_stabilize_reference_content_mapped() -> None:
@ -914,3 +914,12 @@ def test_normalize_ocr_math_text_greek_letter_compound_preserved() -> None:
def test_normalize_ocr_math_text_display_math() -> None:
from paperforge.worker.ocr_math import normalize_ocr_math_text
assert normalize_ocr_math_text("$$ ... $$") == "$$...$$"
def test_section_heading_renders_with_prefix() -> None:
from paperforge.worker.ocr_render import render_fulltext_markdown
blocks = [
{"paper_id": "KEY", "page": 3, "block_id": "b1", "role": "section_heading", "text": "1 Introduction", "render_default": True, "bbox": [80, 200, 500, 230], "page_width": 1200, "page_height": 1700},
]
md = render_fulltext_markdown(structured_blocks=blocks, resolved_metadata={}, figure_inventory={}, table_inventory={})
assert "### 1 Introduction" in md, f"Expected ### prefix, got: {md[:200]}"