Source code for

# 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
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# KIND, either express or implied.  See the License for the
# specific language governing permissions and limitations
# under the License.
"""This module contains Google BigQuery to Google Cloud Storage operator."""
import warnings
from typing import Any, Dict, List, Optional, Sequence, Union

from import TableReference

from airflow.models import BaseOperator
from import BigQueryHook

[docs]class BigQueryToGCSOperator(BaseOperator): """ Transfers a BigQuery table to a Google Cloud Storage bucket. .. seealso:: For more details about these parameters: :param source_project_dataset_table: The dotted ``(<project>.|<project>:)<dataset>.<table>`` BigQuery table to use as the source data. If ``<project>`` is not included, project will be the project defined in the connection json. (templated) :type source_project_dataset_table: str :param destination_cloud_storage_uris: The destination Google Cloud Storage URI (e.g. gs://some-bucket/some-file.txt). (templated) Follows convention defined here: :type destination_cloud_storage_uris: List[str] :param compression: Type of compression to use. :type compression: str :param export_format: File format to export. :type export_format: str :param field_delimiter: The delimiter to use when extracting to a CSV. :type field_delimiter: str :param print_header: Whether to print a header for a CSV file extract. :type print_header: bool :param gcp_conn_id: (Optional) The connection ID used to connect to Google Cloud. :type gcp_conn_id: str :param bigquery_conn_id: (Deprecated) The connection ID used to connect to Google Cloud. This parameter has been deprecated. You should pass the gcp_conn_id parameter instead. :type bigquery_conn_id: str :param delegate_to: The account to impersonate using domain-wide delegation of authority, if any. For this to work, the service account making the request must have domain-wide delegation enabled. :type delegate_to: str :param labels: a dictionary containing labels for the job/query, passed to BigQuery :type labels: dict :param location: The location used for the operation. :type location: str :param impersonation_chain: Optional service account to impersonate using short-term credentials, or chained list of accounts required to get the access_token of the last account in the list, which will be impersonated in the request. If set as a string, the account must grant the originating account the Service Account Token Creator IAM role. If set as a sequence, the identities from the list must grant Service Account Token Creator IAM role to the directly preceding identity, with first account from the list granting this role to the originating account (templated). :type impersonation_chain: Union[str, Sequence[str]] """
[docs] template_fields = ( 'source_project_dataset_table', 'destination_cloud_storage_uris', 'labels', 'impersonation_chain',
[docs] template_ext = ()
[docs] ui_color = '#e4e6f0'
def __init__( self, *, source_project_dataset_table: str, destination_cloud_storage_uris: List[str], compression: str = 'NONE', export_format: str = 'CSV', field_delimiter: str = ',', print_header: bool = True, gcp_conn_id: str = 'google_cloud_default', bigquery_conn_id: Optional[str] = None, delegate_to: Optional[str] = None, labels: Optional[Dict] = None, location: Optional[str] = None, impersonation_chain: Optional[Union[str, Sequence[str]]] = None, **kwargs, ) -> None: super().__init__(**kwargs) if bigquery_conn_id: warnings.warn( "The bigquery_conn_id parameter has been deprecated. You should pass " "the gcp_conn_id parameter.", DeprecationWarning, stacklevel=3, ) gcp_conn_id = bigquery_conn_id self.source_project_dataset_table = source_project_dataset_table self.destination_cloud_storage_uris = destination_cloud_storage_uris self.compression = compression self.export_format = export_format self.field_delimiter = field_delimiter self.print_header = print_header self.gcp_conn_id = gcp_conn_id self.delegate_to = delegate_to self.labels = labels self.location = location self.impersonation_chain = impersonation_chain
[docs] def execute(self, context): 'Executing extract of %s into: %s', self.source_project_dataset_table, self.destination_cloud_storage_uris, ) hook = BigQueryHook( bigquery_conn_id=self.gcp_conn_id, delegate_to=self.delegate_to, location=self.location, impersonation_chain=self.impersonation_chain, ) table_ref = TableReference.from_string(self.source_project_dataset_table, hook.project_id) configuration: Dict[str, Any] = { 'extract': { 'sourceTable': table_ref.to_api_repr(), 'compression': self.compression, 'destinationUris': self.destination_cloud_storage_uris, 'destinationFormat': self.export_format, } } if self.labels: configuration['labels'] = self.labels if self.export_format == 'CSV': # Only set fieldDelimiter and printHeader fields if using CSV. # Google does not like it if you set these fields for other export # formats. configuration['extract']['fieldDelimiter'] = self.field_delimiter configuration['extract']['printHeader'] = self.print_header hook.insert_job(configuration=configuration)

Was this entry helpful?