mirror of
https://github.com/lllin000/PaperForge.git
synced 2026-07-22 06:50:53 +00:00
463cd4d7b1
- Fix references zone detection without heading (backward reference fallback) - Fix reference_item silently dropped in _reorder_tail_run_fifo when no heading - Fix figure proximity matching: use nearest legend regardless of column order - Fix figure numbering in extract_and_write_objects: use actual figure_id - Fix body→reference_item rescue: require text starts with numeric ref pattern - Fix tail reading order rebuilt after block normalization - A8E7SRVS: corrected figure-legend pairing on page 5 - CAQNW9Q2: references now render without heading - K7R8PEKW: adjusted body retention threshold
25 lines
1,003 B
Python
25 lines
1,003 B
Python
import json, sys
|
|
from pathlib import Path
|
|
sys.stdout.reconfigure(encoding="utf-8")
|
|
|
|
p = Path(r"D:\L\OB\Literature-hub\System\PaperForge\ocr\TSCKAVIS\structure\blocks.structured.jsonl")
|
|
rows = [json.loads(line) for line in p.read_text(encoding="utf-8").splitlines() if line.strip()]
|
|
|
|
for i in range(123, 132):
|
|
r = rows[i]
|
|
ctxt = r.get("_container_text") or ""
|
|
print(i, r.get("role"), "has_ct=" + str(bool(ctxt)), r.get("bbox"),
|
|
(r.get("text") or "")[:100],
|
|
"|CT:" + ctxt[:160] if ctxt else "")
|
|
|
|
print("---")
|
|
ftxt = Path(r"D:\L\OB\Literature-hub\System\PaperForge\ocr\TSCKAVIS\fulltext.md").read_text(encoding="utf-8", errors="replace")
|
|
for needle in ["Box 1", "mitochondrial", "Osteoarthritic"]:
|
|
idx = ftxt.lower().find(needle.lower())
|
|
if idx != -1:
|
|
line_start = ftxt.rfind("\n", 0, idx) + 1
|
|
line_end = ftxt.find("\n", idx)
|
|
ctx = ftxt[max(0, idx-40):idx+120]
|
|
print(needle, "->", ctx)
|
|
else:
|
|
print(needle, "-> NOT FOUND")
|