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: reset nopdf OCR status to pending when paper re-enters queue

Browse source
This commit is contained in:
Research Assistant 2026-05-14 18:43:48 +08:00
parent ffd4eb7ca2
commit fe36dcfe10
1 changed files with 12 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
paperforge/worker/ocr.py
View file

@ -190,6 +190,8 @@ def sync_ocr_queue(paths: dict[str, Path], target_rows: list[dict]) -> list[dict
status = str(meta.get("ocr_status", "pending") or "pending").strip().lower()
if status in {"done", "blocked"}:
continue
if status == "nopdf":
status = "pending"
synced = dict(row)
synced["has_pdf"] = bool(target.get("has_pdf"))
synced["pdf_path"] = target.get("pdf_path", "")
@ -210,6 +212,9 @@ def sync_ocr_queue(paths: dict[str, Path], target_rows: list[dict]) -> list[dict
status = str(meta.get("ocr_status", "pending") or "pending").strip().lower()
if status in {"done", "blocked"}:
continue
if status == "nopdf":
status = "pending"
continue
synced_queue.append(
{
"zotero_key": key,
@ -1571,13 +1576,19 @@ def run_ocr(vault: Path, verbose: bool = False, no_progress: bool = False) -> in
for row in target_rows:
key = row["zotero_key"]
meta = ensure_ocr_meta(vault, row)
if str(meta.get("ocr_status", "") or "").strip().lower() == "error":
current = str(meta.get("ocr_status", "") or "").strip().lower()
if current == "error":
meta["ocr_status"] = "pending"
meta["ocr_job_id"] = ""
meta["ocr_started_at"] = ""
meta["ocr_finished_at"] = ""
meta["retry_count"] = 0
write_json(paths["ocr"] / key / "meta.json", meta)
elif current == "nopdf":
meta["ocr_status"] = "pending"
meta["error"] = ""
meta["retry_count"] = 0
write_json(paths["ocr"] / key / "meta.json", meta)
status, _error = validate_ocr_meta(paths, meta)
if status == "done_incomplete":
meta["ocr_status"] = "pending"