Source code for airflow.providers.google.cloud.triggers.dataproc

#
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements.  See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership.  The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License.  You may obtain a copy of the License at
#
#   http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied.  See the License for the
# specific language governing permissions and limitations
# under the License.
"""This module contains Google Dataproc triggers."""
from __future__ import annotations

import asyncio
from typing import Sequence

from google.cloud.dataproc_v1 import JobStatus

from airflow import AirflowException
from airflow.providers.google.cloud.hooks.dataproc import DataprocAsyncHook
from airflow.triggers.base import BaseTrigger, TriggerEvent


[docs]class DataprocBaseTrigger(BaseTrigger):
    """
    Trigger that periodically polls information from Dataproc API to verify job status.
    Implementation leverages asynchronous transport.
    """

    def __init__(
        self,
        job_id: str,
        region: str,
        project_id: str | None = None,
        gcp_conn_id: str = "google_cloud_default",
        impersonation_chain: str | Sequence[str] | None = None,
        delegate_to: str | None = None,
        polling_interval_seconds: int = 30,
    ):
        super().__init__()
        self.gcp_conn_id = gcp_conn_id
        self.impersonation_chain = impersonation_chain
        self.job_id = job_id
        self.project_id = project_id
        self.region = region
        self.polling_interval_seconds = polling_interval_seconds
        self.delegate_to = delegate_to
        self.hook = DataprocAsyncHook(
            delegate_to=self.delegate_to,
            gcp_conn_id=self.gcp_conn_id,
            impersonation_chain=self.impersonation_chain,
        )

[docs]    def serialize(self):
        return (
            "airflow.providers.google.cloud.triggers.dataproc.DataprocBaseTrigger",
            {
                "job_id": self.job_id,
                "project_id": self.project_id,
                "region": self.region,
                "gcp_conn_id": self.gcp_conn_id,
                "delegate_to": self.delegate_to,
                "impersonation_chain": self.impersonation_chain,
                "polling_interval_seconds": self.polling_interval_seconds,
            },
        )

[docs]    async def run(self):
        while True:
            job = await self.hook.get_job(project_id=self.project_id, region=self.region, job_id=self.job_id)
            state = job.status.state
            self.log.info("Dataproc job: %s is in state: %s", self.job_id, state)
            if state in (JobStatus.State.ERROR, JobStatus.State.DONE, JobStatus.State.CANCELLED):
                if state in (JobStatus.State.DONE, JobStatus.State.CANCELLED):
                    break
                elif state == JobStatus.State.ERROR:
                    raise AirflowException(f"Dataproc job execution failed {self.job_id}")
            await asyncio.sleep(self.polling_interval_seconds)
        yield TriggerEvent({"job_id": self.job_id, "job_state": state})