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.
"""Transfers data from AWS Redshift into a S3 Bucket."""
from __future__ import annotations

from typing import TYPE_CHECKING, Iterable, Mapping, Sequence

from airflow.exceptions import AirflowException
from airflow.models import BaseOperator
from import RedshiftDataHook
from import RedshiftSQLHook
from import S3Hook
from import build_credentials_block

    from airflow.utils.context import Context

[docs]class RedshiftToS3Operator(BaseOperator): """ Execute an UNLOAD command to s3 as a CSV with headers. .. seealso:: For more information on how to use this operator, take a look at the guide: :ref:`howto/operator:RedshiftToS3Operator` :param s3_bucket: reference to a specific S3 bucket :param s3_key: reference to a specific S3 key. If ``table_as_file_name`` is set to False, this param must include the desired file name :param schema: reference to a specific schema in redshift database Applicable when ``table`` param provided. :param table: reference to a specific table in redshift database Used when ``select_query`` param not provided. :param select_query: custom select query to fetch data from redshift database :param redshift_conn_id: reference to a specific redshift database :param aws_conn_id: reference to a specific S3 connection If the AWS connection contains 'aws_iam_role' in ``extras`` the operator will use AWS STS credentials with a token :param verify: Whether or not to verify SSL certificates for S3 connection. By default SSL certificates are verified. You can provide the following values: - ``False``: do not validate SSL certificates. SSL will still be used (unless use_ssl is False), but SSL certificates will not be verified. - ``path/to/cert/bundle.pem``: A filename of the CA cert bundle to uses. You can specify this argument if you want to use a different CA cert bundle than the one used by botocore. :param unload_options: reference to a list of UNLOAD options :param autocommit: If set to True it will automatically commit the UNLOAD statement. Otherwise it will be committed right before the redshift connection gets closed. :param include_header: If set to True the s3 file contains the header columns. :param parameters: (optional) the parameters to render the SQL query with. :param table_as_file_name: If set to True, the s3 file will be named as the table. Applicable when ``table`` param provided. :param redshift_data_api_kwargs: If using the Redshift Data API instead of the SQL-based connection, dict of arguments for the hook's ``execute_query`` method. Cannot include any of these kwargs: ``{'sql', 'parameters'}`` """
[docs] template_fields: Sequence[str] = ( "s3_bucket", "s3_key", "schema", "table", "unload_options", "select_query", "redshift_conn_id", )
[docs] template_ext: Sequence[str] = (".sql",)
[docs] template_fields_renderers = {"select_query": "sql"}
[docs] ui_color = "#ededed"
def __init__( self, *, s3_bucket: str, s3_key: str, schema: str | None = None, table: str | None = None, select_query: str | None = None, redshift_conn_id: str = "redshift_default", aws_conn_id: str = "aws_default", verify: bool | str | None = None, unload_options: list | None = None, autocommit: bool = False, include_header: bool = False, parameters: Iterable | Mapping | None = None, table_as_file_name: bool = True, # Set to True by default for not breaking current workflows redshift_data_api_kwargs: dict = {}, **kwargs, ) -> None: super().__init__(**kwargs) self.s3_bucket = s3_bucket self.s3_key = f"{s3_key}/{table}_" if (table and table_as_file_name) else s3_key self.schema = schema self.table = table self.redshift_conn_id = redshift_conn_id self.aws_conn_id = aws_conn_id self.verify = verify self.unload_options: list = unload_options or [] self.autocommit = autocommit self.include_header = include_header self.parameters = parameters self.table_as_file_name = table_as_file_name self.redshift_data_api_kwargs = redshift_data_api_kwargs if select_query: self.select_query = select_query elif self.schema and self.table: self.select_query = f"SELECT * FROM {self.schema}.{self.table}" else: raise ValueError( "Please provide both `schema` and `table` params or `select_query` to fetch the data." ) if self.include_header and "HEADER" not in [uo.upper().strip() for uo in self.unload_options]: self.unload_options = [*self.unload_options, "HEADER"] if self.redshift_data_api_kwargs: for arg in ["sql", "parameters"]: if arg in self.redshift_data_api_kwargs: raise AirflowException(f"Cannot include param '{arg}' in Redshift Data API kwargs") def _build_unload_query( self, credentials_block: str, select_query: str, s3_key: str, unload_options: str ) -> str: return f""" UNLOAD ('{select_query}') TO 's3://{self.s3_bucket}/{s3_key}' credentials '{credentials_block}' {unload_options}; """
[docs] def execute(self, context: Context) -> None: redshift_hook: RedshiftDataHook | RedshiftSQLHook if self.redshift_data_api_kwargs: redshift_hook = RedshiftDataHook(aws_conn_id=self.redshift_conn_id) else: redshift_hook = RedshiftSQLHook(redshift_conn_id=self.redshift_conn_id) conn = S3Hook.get_connection(conn_id=self.aws_conn_id) if conn.extra_dejson.get("role_arn", False): credentials_block = f"aws_iam_role={conn.extra_dejson['role_arn']}" else: s3_hook = S3Hook(aws_conn_id=self.aws_conn_id, verify=self.verify) credentials = s3_hook.get_credentials() credentials_block = build_credentials_block(credentials) unload_options = "\n\t\t\t".join(self.unload_options) unload_query = self._build_unload_query( credentials_block, self.select_query, self.s3_key, unload_options )"Executing UNLOAD command...") if isinstance(redshift_hook, RedshiftDataHook): redshift_hook.execute_query( sql=unload_query, parameters=self.parameters, **self.redshift_data_api_kwargs ) else:, self.autocommit, parameters=self.parameters)"UNLOAD command complete...")

Was this entry helpful?