2023-05-15 08:51:32 +08:00
|
|
|
import logging
|
|
|
|
import time
|
|
|
|
|
|
|
|
import click
|
|
|
|
from celery import shared_task
|
2024-01-12 12:34:01 +08:00
|
|
|
from core.indexing_runner import DocumentIsPausedException, IndexingRunner
|
2023-05-15 08:51:32 +08:00
|
|
|
from extensions.ext_database import db
|
|
|
|
from models.dataset import Document
|
2024-01-12 12:34:01 +08:00
|
|
|
from werkzeug.exceptions import NotFound
|
2023-05-15 08:51:32 +08:00
|
|
|
|
|
|
|
|
2023-07-31 13:13:08 +08:00
|
|
|
@shared_task(queue='dataset')
|
2023-05-15 08:51:32 +08:00
|
|
|
def recover_document_indexing_task(dataset_id: str, document_id: str):
|
|
|
|
"""
|
|
|
|
Async recover document
|
|
|
|
:param dataset_id:
|
|
|
|
:param document_id:
|
|
|
|
|
|
|
|
Usage: recover_document_indexing_task.delay(dataset_id, document_id)
|
|
|
|
"""
|
|
|
|
logging.info(click.style('Recover document: {}'.format(document_id), fg='green'))
|
|
|
|
start_at = time.perf_counter()
|
|
|
|
|
|
|
|
document = db.session.query(Document).filter(
|
|
|
|
Document.id == document_id,
|
|
|
|
Document.dataset_id == dataset_id
|
|
|
|
).first()
|
|
|
|
|
|
|
|
if not document:
|
|
|
|
raise NotFound('Document not found')
|
|
|
|
|
|
|
|
try:
|
|
|
|
indexing_runner = IndexingRunner()
|
|
|
|
if document.indexing_status in ["waiting", "parsing", "cleaning"]:
|
2023-06-16 21:47:51 +08:00
|
|
|
indexing_runner.run([document])
|
2023-05-15 08:51:32 +08:00
|
|
|
elif document.indexing_status == "splitting":
|
|
|
|
indexing_runner.run_in_splitting_status(document)
|
|
|
|
elif document.indexing_status == "indexing":
|
|
|
|
indexing_runner.run_in_indexing_status(document)
|
|
|
|
end_at = time.perf_counter()
|
|
|
|
logging.info(click.style('Processed document: {} latency: {}'.format(document.id, end_at - start_at), fg='green'))
|
2023-06-25 16:49:14 +08:00
|
|
|
except DocumentIsPausedException as ex:
|
|
|
|
logging.info(click.style(str(ex), fg='yellow'))
|
|
|
|
except Exception:
|
|
|
|
pass
|