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

chore: remove stale debug script _check_rebuild.py

Browse source
This commit is contained in:
Research Assistant 2026-06-26 23:19:56 +08:00
parent c4036cbde5
commit 7dcb73b068
1 changed files with 0 additions and 50 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

50
_check_rebuild.py
View file

@ -1,50 +0,0 @@
from pathlib import Path
import json
vault = Path(r"D:\L\OB\Literature-hub")
structured_path = vault / "System" / "PaperForge" / "ocr" / "SAN9AYVR" / "blocks.structured.jsonl"
profiles_path = vault / "System" / "PaperForge" / "ocr" / "SAN9AYVR" / "role_span_profiles.json"
if structured_path.exists():
print(f"structured blocks: {structured_path.stat().st_size} bytes")
with open(structured_path, encoding="utf-8") as f:
line = f.readline()
row = json.loads(line)
has_span = "span_metadata" in row
has_role = row.get("role")
has_conf = row.get("role_confidence")
print(f" first block role={has_role}, conf={has_conf}, has_span_metadata={has_span}")
total = 0
with_span = 0
with open(structured_path, encoding="utf-8") as f:
for line in f:
total += 1
row = json.loads(line)
if row.get("span_metadata"):
with_span += 1
print(f" total blocks: {total}, with span_metadata: {with_span} ({100*with_span/total:.1f}%)")
else:
print("structured blocks not found")
if profiles_path.exists():
profiles = json.loads(profiles_path.read_text(encoding="utf-8"))
print(f"\nrole_span_profiles.json: {len(profiles)} roles")
for role, p in sorted(profiles.items()):
print(f" {role}: count={p['block_count']}, size={p['mean_size']}, quality={p['quality']}")
else:
print("role_span_profiles.json not found")
second_pass_total = 0
span_alt_total = 0
with open(structured_path, encoding="utf-8") as f:
for line in f:
row = json.loads(line)
ev = row.get("evidence", [])
for e in ev:
if "second_pass" in e:
second_pass_total += 1
if "span_alternatives" in e:
span_alt_total += 1
print(f"\nSecond-pass applied: {second_pass_total} blocks")
print(f"Span alternatives flagged: {span_alt_total} blocks")