tjdify/api/tasks/recover_document_indexing_task.py

import datetime
import logging
import time

import click
from celery import shared_task
from werkzeug.exceptions import NotFound

from core.indexing_runner import IndexingRunner, DocumentIsPausedException
from extensions.ext_database import db
from models.dataset import Document


@shared_task
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"]:
            indexing_runner.run(document)
        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'))
    except DocumentIsPausedException:
        logging.info(click.style('Document paused, document id: {}'.format(document.id), fg='yellow'))
    except Exception as e:
        logging.exception("consume document failed")
        document.indexing_status = 'error'
        document.error = str(e)
        document.stopped_at = datetime.datetime.utcnow()
        db.session.commit()