mirror of
https://github.com/lllin000/PaperForge.git
synced 2026-07-22 06:50:53 +00:00
f9dff20cd8
- Add RegionPrepass data model for frontmatter/structured_insert/body classification - Add PDF visual container detection (filled rects) for sidebar detection - Add Box N and keyword-based sidebar anchor detection - Add column-aware block expansion for mixed sidebar clusters - Add _container_text from PDF text blocks for cross-column truncation - Add degraded-mode heading level normalization with font size clustering - Merge adjacent structured_insert blocks into single callout - Fix metadata enrichment from Literature-hub note frontmatter for old papers - Fix heading hierarchy using span font-size clusters when available - Add real-paper regression harness (TSCKAVIS, CAQNW9Q2, A8E7SRVS, K7R8PEKW) - Add body retention, heading, metadata, and callout acceptance tests - 219 passed, 4 control guards passed
37 lines
1.5 KiB
Python
37 lines
1.5 KiB
Python
from __future__ import annotations
|
|
|
|
|
|
def test_render_fulltext_uses_resolved_metadata_and_object_links(tmp_path) -> None:
|
|
from paperforge.worker.ocr_render import render_fulltext_markdown
|
|
|
|
structured_blocks = [
|
|
{"page": 1, "block_id": "p1_b1", "role": "abstract_heading", "text": "Abstract", "render_default": True},
|
|
{"page": 1, "block_id": "p1_b2", "role": "abstract_body", "text": "Background text.", "render_default": True},
|
|
{"page": 2, "block_id": "p2_b1", "role": "section_heading", "text": "1 Introduction", "render_default": True},
|
|
{"page": 2, "block_id": "p2_b2", "role": "body_paragraph", "text": "Intro body.", "render_default": True},
|
|
]
|
|
resolved_metadata = {
|
|
"title": {"value": "Paper Title"},
|
|
"authors": {"value": ["Alice", "Bob"]},
|
|
"journal": {"value": "Journal A"},
|
|
"year": {"value": 2024},
|
|
"doi": {"value": "10.1000/xyz"},
|
|
}
|
|
figure_inventory = {
|
|
"matched_figures": [{"figure_id": "figure_001", "confidence": 0.91, "flags": []}],
|
|
}
|
|
table_inventory = {
|
|
"tables": [{"table_id": "table_001", "has_asset": True}],
|
|
}
|
|
|
|
md = render_fulltext_markdown(
|
|
structured_blocks=structured_blocks,
|
|
resolved_metadata=resolved_metadata,
|
|
figure_inventory=figure_inventory,
|
|
table_inventory=table_inventory,
|
|
)
|
|
|
|
assert "# Paper Title" in md
|
|
assert "Authors:" in md
|
|
assert "## 1 Introduction" in md
|
|
assert "![[figures/figure_001.md]]" in md or "![[render/figures/figure_001.md]]" in md
|