feluelle commented on a change in pull request #10947: URL: https://github.com/apache/airflow/pull/10947#discussion_r496528486
########## File path: airflow/providers/amazon/aws/operators/glacier.py ########## @@ -0,0 +1,91 @@ +# +# 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. +from airflow.models import BaseOperator +from airflow.providers.amazon.aws.hooks.glacier import GlacierHook +from airflow.utils.decorators import apply_defaults + + +class GlacierCreateJobOperator(BaseOperator): + """ + Initiate an Amazon Glacier inventory-retrieval job + + .. seealso:: + For more information on how to use this operator, take a look at the guide: + :ref:`howto/operator:GlacierCreateJobOperator` + + + :param vault_name: the Glacier vault on which job is executed + :type vault_name: str + """ + + template_fields = ("vault_name",) + + @apply_defaults + def __init__( + self, + *, + aws_conn_id="aws_default", + vault_name: str, + **kwargs, + ): + super().__init__(**kwargs) + self.aws_conn_id = aws_conn_id + self.vault_name = vault_name + + def execute(self, context): + hook = GlacierHook(aws_conn_id=self.aws_conn_id) + response = hook.retrieve_inventory(vault_name=self.vault_name) + self.xcom_push(context, key="job_id", value=response['ResponseMetadata']['HTTPStatusCode']) Review comment: ```suggestion ``` I personally think that this is not needed. I would suggest to remove that and return only the whole `response` like what you already have. Or only return `response['ResponseMetadata']['HTTPStatusCode']` which may be enough for tasks that depend on it. WDYT? ########## File path: airflow/providers/amazon/aws/sensors/glacier.py ########## @@ -0,0 +1,75 @@ +# +# 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. + +from typing import Any + +from airflow.exceptions import AirflowException +from airflow.providers.amazon.aws.hooks.glacier import GlacierHook +from airflow.sensors.base_sensor_operator import BaseSensorOperator +from airflow.utils.decorators import apply_defaults + + +class GlacierJobOperationSensor(BaseSensorOperator): + """ + Glacier sensor for checking job state. This operator runs only in reschedule mode. + + :param vault_name: name of Glacier vault on which job is executed + :type vault_name: str + :param job_id: the job ID was returned by retrieve_inventory() + :type job_id: str + """ + + template_fields = ["vault_name", "job_id"] + + IN_PROGRESS = "InProgress" + SUCCEEDED = "Succeeded" Review comment: WDYT of having a class of type enum? ```python class JobStatus(Enum): IN_PROGRESS = "InProgress" SUCCEEDED = "Succeeded" ``` ########## File path: airflow/providers/amazon/aws/transfers/glacier_to_gcs.py ########## @@ -0,0 +1,103 @@ +# +# 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. +import tempfile +from typing import Optional, Union, Sequence + +from airflow.models import BaseOperator +from airflow.providers.amazon.aws.hooks.glacier import GlacierHook +from airflow.providers.google.cloud.hooks.gcs import GCSHook +from airflow.utils.decorators import apply_defaults + + +class GlacierToGCSOperator(BaseOperator): + """ + This operator transfers data from Glacier to Google Cloud Storage + + .. seealso:: + For more information on how to use this operator, take a look at the guide: + :ref:`howto/operator:GlacierToGCSOperator` + + :param vault_name: the Glacier vault on which job is executed + :type vault_name: string + :param bucket_name: the Google Cloud Storage bucket where the data will be transferred + :type bucket_name: str + :param object_name: the name of the object to check in the Google cloud + storage bucket. + :type object_name: str + :param gzip: option to compress local file or file data for upload + :type gzip: bool + :param google_impersonation_chain: Optional Google 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 google_impersonation_chain: Union[str, Sequence[str]] Review comment: Please check that you keep it in the same order as it is in init. ########## File path: airflow/providers/amazon/aws/transfers/glacier_to_gcs.py ########## @@ -0,0 +1,103 @@ +# +# 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. +import tempfile +from typing import Optional, Union, Sequence + +from airflow.models import BaseOperator +from airflow.providers.amazon.aws.hooks.glacier import GlacierHook +from airflow.providers.google.cloud.hooks.gcs import GCSHook +from airflow.utils.decorators import apply_defaults + + +class GlacierToGCSOperator(BaseOperator): + """ + This operator transfers data from Glacier to Google Cloud Storage + + .. seealso:: + For more information on how to use this operator, take a look at the guide: + :ref:`howto/operator:GlacierToGCSOperator` + + :param vault_name: the Glacier vault on which job is executed + :type vault_name: string + :param bucket_name: the Google Cloud Storage bucket where the data will be transferred + :type bucket_name: str + :param object_name: the name of the object to check in the Google cloud + storage bucket. + :type object_name: str + :param gzip: option to compress local file or file data for upload + :type gzip: bool + :param google_impersonation_chain: Optional Google 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 google_impersonation_chain: Union[str, Sequence[str]] + """ + + template_fields = ("vault_name", "bucket_name", "object_name") + + @apply_defaults + def __init__( + self, + *, + aws_conn_id="aws_default", + vault_name: str, + gcp_conn_id="google_cloud_default", + delegate_to=None, + google_impersonation_chain: Optional[Union[str, Sequence[str]]] = None, + bucket_name: str, + object_name: str, + gzip: bool, + **kwargs, + ): + super().__init__(**kwargs) + self.aws_conn_id = aws_conn_id + self.vault_name = vault_name + self.gcp_conn_id = gcp_conn_id + self.delegate_to = delegate_to + self.impersonation_chain = google_impersonation_chain + self.bucket_name = bucket_name + self.object_name = object_name + self.gzip = gzip + + def execute(self, context): + glacier_hook = GlacierHook(aws_conn_id=self.aws_conn_id) + gcs_hook = GCSHook( + gcp_conn_id=self.gcp_conn_id, + delegate_to=self.delegate_to, + impersonation_chain=self.impersonation_chain, + ) + job_id = glacier_hook.retrieve_inventory(vault_name=self.vault_name) + # glacier_data = glacier_hook.retrieve_inventory_results( + # vault_name=self.vault_name, job_id=job_id["jobId"]) + with tempfile.NamedTemporaryFile() as temp_file: + glacier_data = glacier_hook.retrieve_inventory_results( + vault_name=self.vault_name, job_id=job_id["jobId"] + ) + temp_file.write(glacier_data) + temp_file.flush() + gcs_hook.upload( + bucket_name=self.bucket_name, + object_name=self.object_name, + filename=temp_file.name, + gzip=self.gzip, + ) Review comment: It is important that the user of this operators know that it works like that. I mean copying files to the local instance must be done with caution. Airflow may not be running on a big machine with sufficient memory, etc. So I would suggest that you just add a `.. note::` to the docs of the operator at the top of the class. And to the howto docs as well. WDYT? ########## File path: airflow/providers/amazon/aws/transfers/glacier_to_gcs.py ########## @@ -0,0 +1,103 @@ +# +# 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. +import tempfile +from typing import Optional, Union, Sequence + +from airflow.models import BaseOperator +from airflow.providers.amazon.aws.hooks.glacier import GlacierHook +from airflow.providers.google.cloud.hooks.gcs import GCSHook +from airflow.utils.decorators import apply_defaults + + +class GlacierToGCSOperator(BaseOperator): + """ + This operator transfers data from Glacier to Google Cloud Storage + + .. seealso:: + For more information on how to use this operator, take a look at the guide: + :ref:`howto/operator:GlacierToGCSOperator` + + :param vault_name: the Glacier vault on which job is executed + :type vault_name: string + :param bucket_name: the Google Cloud Storage bucket where the data will be transferred + :type bucket_name: str + :param object_name: the name of the object to check in the Google cloud + storage bucket. + :type object_name: str + :param gzip: option to compress local file or file data for upload + :type gzip: bool + :param google_impersonation_chain: Optional Google 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 google_impersonation_chain: Union[str, Sequence[str]] + """ + + template_fields = ("vault_name", "bucket_name", "object_name") + + @apply_defaults + def __init__( + self, + *, + aws_conn_id="aws_default", + vault_name: str, + gcp_conn_id="google_cloud_default", + delegate_to=None, + google_impersonation_chain: Optional[Union[str, Sequence[str]]] = None, + bucket_name: str, + object_name: str, + gzip: bool, + **kwargs, + ): + super().__init__(**kwargs) + self.aws_conn_id = aws_conn_id + self.vault_name = vault_name + self.gcp_conn_id = gcp_conn_id + self.delegate_to = delegate_to + self.impersonation_chain = google_impersonation_chain + self.bucket_name = bucket_name + self.object_name = object_name + self.gzip = gzip + + def execute(self, context): + glacier_hook = GlacierHook(aws_conn_id=self.aws_conn_id) + gcs_hook = GCSHook( + gcp_conn_id=self.gcp_conn_id, + delegate_to=self.delegate_to, + impersonation_chain=self.impersonation_chain, + ) + job_id = glacier_hook.retrieve_inventory(vault_name=self.vault_name) + # glacier_data = glacier_hook.retrieve_inventory_results( + # vault_name=self.vault_name, job_id=job_id["jobId"]) Review comment: ```suggestion ``` ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected]
