mirror of
https://github.com/lllin000/PaperForge.git
synced 2026-07-22 17:00:23 +00:00
05629bce82
Core contract: - ErrorCode: 8→26 with _missing_() graceful degradation for unknown codes - PFResult: +warnings/next_actions, PFError: +suggestions - OcrStatus: 4→9 granular states (NONE/QUEUED/BLOCKED/NO_PDF/DONE_INCOMPLETE restored 1:1) - field_registry.yaml: +owner/deprecated/replacement/enum values/default Adapter cleanup: - new core/io.py (read_json/write_json), core/date_utils.py (extract_year) - new adapters/collections.py (build_collection_lookup) - adapters/bbt.py: cut worker dependency, _private→public+alias - worker/_utils.py + _domain.py: re-export from core instead of duplicate defs Command unification: - All 6 commands (sync/status/ocr/deep/repair/dashboard) → PFResult - cli.py --json dest unified to 'json' (was json_output on status/doctor) - commands/sync.py → SyncService (no more int/dict/PFResult mixing) Service hardening: - SyncService.run() orchestrates full sync lifecycle (select→index→clean) - cleanup loops (orphaned records, flat notes) migrated from worker - worker/sync.py: freeze line + services→worker one-way dependency - plugin/main.js: formal-library.json fallback deprecation warning Verification: 181/181 tests, 0 new lint errors
77 lines
2.2 KiB
Python
77 lines
2.2 KiB
Python
"""Deep-reading queue command."""
|
|
|
|
import argparse
|
|
import logging
|
|
from pathlib import Path
|
|
|
|
from paperforge import __version__
|
|
from paperforge.core.result import PFResult
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
def _get_run_deep_reading():
|
|
"""Get run_deep_reading, preferring cli patches if available."""
|
|
try:
|
|
from paperforge.cli import run_deep_reading
|
|
|
|
if run_deep_reading is not None:
|
|
return run_deep_reading
|
|
except Exception:
|
|
pass
|
|
|
|
import sys
|
|
|
|
repo_root = Path(__file__).resolve().parent.parent.parent
|
|
if str(repo_root) not in sys.path:
|
|
sys.path.insert(0, str(repo_root))
|
|
from paperforge.worker.deep_reading import run_deep_reading
|
|
|
|
return run_deep_reading
|
|
|
|
|
|
def run(args: argparse.Namespace) -> int:
|
|
"""Run deep-reading queue check. Supports --json for PFResult output."""
|
|
vault = getattr(args, "vault_path", None)
|
|
if vault is None:
|
|
from paperforge.config import resolve_vault
|
|
|
|
vault = resolve_vault(cli_vault=getattr(args, "vault", None))
|
|
|
|
json_output = getattr(args, "json", False)
|
|
run_deep_reading = _get_run_deep_reading()
|
|
exit_code = run_deep_reading(vault, verbose=getattr(args, "verbose", False))
|
|
|
|
if json_output:
|
|
from paperforge.worker._utils import get_analyze_queue
|
|
|
|
queue = get_analyze_queue(vault)
|
|
ready = [r for r in queue if r.get("ocr_status") == "done"]
|
|
blocked = [r for r in queue if r.get("ocr_status") != "done"]
|
|
|
|
pf = PFResult(
|
|
ok=True,
|
|
command="deep-reading",
|
|
version=__version__,
|
|
data={
|
|
"queue": [
|
|
{
|
|
"zotero_key": r["zotero_key"],
|
|
"domain": r["domain"],
|
|
"title": r["title"],
|
|
"ocr_status": r.get("ocr_status", "pending"),
|
|
"ready": r.get("ocr_status") == "done",
|
|
}
|
|
for r in queue
|
|
],
|
|
"summary": {
|
|
"total": len(queue),
|
|
"ready": len(ready),
|
|
"blocked": len(blocked),
|
|
},
|
|
},
|
|
)
|
|
print(pf.to_json())
|
|
return 0
|
|
|
|
return exit_code
|