| |
| |
| <!-- |
| Javascript to render AIRFLOW-XXX and PR references in text |
| as HTML links. |
| |
| Overrides extrahead block from sphinx_rtd_theme |
| https://www.sphinx-doc.org/en/master/templating.html |
| --> |
| |
| |
| <!DOCTYPE html> |
| <!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]--> |
| <!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]--> |
| <head> |
| <meta charset="utf-8"> |
| |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> |
| |
| <title>airflow.contrib.example_dags.example_gcp_transfer — Airflow Documentation</title> |
| |
| |
| |
| |
| <link rel="shortcut icon" href="../../../../_static/pin_32.png"/> |
| |
| |
| |
| |
| |
| <script type="text/javascript" src="../../../../_static/js/modernizr.min.js"></script> |
| |
| |
| <script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script> |
| <script type="text/javascript" src="../../../../_static/jquery.js"></script> |
| <script type="text/javascript" src="../../../../_static/underscore.js"></script> |
| <script type="text/javascript" src="../../../../_static/doctools.js"></script> |
| <script type="text/javascript" src="../../../../_static/language_data.js"></script> |
| <script type="text/javascript" src="../../../../_static/jira-links.js"></script> |
| |
| <script type="text/javascript" src="../../../../_static/js/theme.js"></script> |
| |
| |
| |
| |
| <link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../../_static/graphviz.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../../_static/exampleinclude.css" type="text/css" /> |
| <link rel="index" title="Index" href="../../../../genindex.html" /> |
| <link rel="search" title="Search" href="../../../../search.html" /> |
| |
| <script> |
| </script> |
| <style> |
| |
| </style> |
| |
| </head> |
| |
| <body class="wy-body-for-nav"> |
| |
| |
| <div class="wy-grid-for-nav"> |
| |
| <nav data-toggle="wy-nav-shift" class="wy-nav-side"> |
| <div class="wy-side-scroll"> |
| <div class="wy-side-nav-search" > |
| |
| |
| |
| <a href="../../../../index.html" class="icon icon-home"> Airflow |
| |
| |
| |
| </a> |
| |
| |
| |
| |
| <div class="version"> |
| 1.10.8 |
| </div> |
| |
| |
| |
| |
| <div role="search"> |
| <form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get"> |
| <input type="text" name="q" placeholder="Search docs" /> |
| <input type="hidden" name="check_keywords" value="yes" /> |
| <input type="hidden" name="area" value="default" /> |
| </form> |
| </div> |
| |
| |
| </div> |
| |
| <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> |
| |
| |
| |
| |
| |
| |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../project.html">Project</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../license.html">License</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../start.html">Quick Start</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../installation.html">Installation</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../tutorial.html">Tutorial</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../howto/index.html">How-to Guides</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../ui.html">UI / Screenshots</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../concepts.html">Concepts</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../profiling.html">Data Profiling</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../cli.html">Command Line Interface Reference</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling & Triggers</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../executor/index.html">Executor</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../plugins.html">Plugins</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../security.html">Security</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../timezone.html">Time zones</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../api.html">REST API Reference</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../integration.html">Integration</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../metrics.html">Metrics</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../errors.html">Error Tracking</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../kubernetes.html">Kubernetes</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../lineage.html">Lineage</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../dag-serialization.html">DAG Serialization</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../changelog.html">Changelog</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../best-practices.html">Best Practices</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../faq.html">FAQ</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../macros.html">Macros reference</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../privacy_notice.html">Privacy Notice</a></li> |
| </ul> |
| <p class="caption"><span class="caption-text">References</span></p> |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../_api/index.html">Python API</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../configurations-ref.html">Configurations</a></li> |
| </ul> |
| |
| |
| |
| </div> |
| </div> |
| </nav> |
| |
| <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> |
| |
| |
| <nav class="wy-nav-top" aria-label="top navigation"> |
| |
| <i data-toggle="wy-nav-top" class="fa fa-bars"></i> |
| <a href="../../../../index.html">Airflow</a> |
| |
| </nav> |
| |
| |
| <div class="wy-nav-content"> |
| |
| <div class="rst-content"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <div role="navigation" aria-label="breadcrumbs navigation"> |
| |
| <ul class="wy-breadcrumbs"> |
| |
| <li><a href="../../../../index.html">Docs</a> »</li> |
| |
| <li><a href="../../../index.html">Module code</a> »</li> |
| |
| <li>airflow.contrib.example_dags.example_gcp_transfer</li> |
| |
| |
| <li class="wy-breadcrumbs-aside"> |
| |
| </li> |
| |
| </ul> |
| |
| |
| <hr/> |
| </div> |
| <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> |
| <div itemprop="articleBody"> |
| |
| <h1>Source code for airflow.contrib.example_dags.example_gcp_transfer</h1><div class="highlight"><pre> |
| <span></span><span class="c1"># -*- coding: utf-8 -*-</span> |
| <span class="c1">#</span> |
| <span class="c1"># Licensed to the Apache Software Foundation (ASF) under one</span> |
| <span class="c1"># or more contributor license agreements. See the NOTICE file</span> |
| <span class="c1"># distributed with this work for additional information</span> |
| <span class="c1"># regarding copyright ownership. The ASF licenses this file</span> |
| <span class="c1"># to you under the Apache License, Version 2.0 (the</span> |
| <span class="c1"># "License"); you may not use this file except in compliance</span> |
| <span class="c1"># with the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing,</span> |
| <span class="c1"># software distributed under the License is distributed on an</span> |
| <span class="c1"># "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span> |
| <span class="c1"># KIND, either express or implied. See the License for the</span> |
| <span class="c1"># specific language governing permissions and limitations</span> |
| <span class="c1"># under the License.</span> |
| |
| <span class="sd">"""</span> |
| <span class="sd">Example Airflow DAG that demonstrates interactions with Google Cloud Transfer.</span> |
| |
| |
| <span class="sd">This DAG relies on the following OS environment variables</span> |
| |
| <span class="sd">* GCP_PROJECT_ID - Google Cloud Project to use for the Google Cloud Transfer Service.</span> |
| <span class="sd">* GCP_DESCRIPTION - Description of transfer job</span> |
| <span class="sd">* GCP_TRANSFER_SOURCE_AWS_BUCKET - Amazon Web Services Storage bucket from which files are copied.</span> |
| <span class="sd"> .. warning::</span> |
| <span class="sd"> You need to provide a large enough set of data so that operations do not execute too quickly.</span> |
| <span class="sd"> Otherwise, DAG will fail.</span> |
| <span class="sd">* GCP_TRANSFER_FIRST_TARGET_BUCKET - Google Cloud Storage bucket to which files are copied from AWS.</span> |
| <span class="sd"> It is also a source bucket in next step</span> |
| <span class="sd">* GCP_TRANSFER_SECOND_TARGET_BUCKET - Google Cloud Storage bucket bucket to which files are copied</span> |
| <span class="sd">* WAIT_FOR_OPERATION_POKE_INTERVAL - interval of what to check the status of the operation</span> |
| <span class="sd"> A smaller value than the default value accelerates the system test and ensures its correct execution with</span> |
| <span class="sd"> smaller quantities of files in the source bucket</span> |
| <span class="sd"> Look at documentation of :class:`~airflow.operators.sensors.BaseSensorOperator` for more information</span> |
| |
| <span class="sd">"""</span> |
| <span class="kn">import</span> <span class="nn">os</span> |
| <span class="kn">from</span> <span class="nn">datetime</span> <span class="kn">import</span> <span class="n">datetime</span><span class="p">,</span> <span class="n">timedelta</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Any</span><span class="p">,</span> <span class="n">Dict</span> |
| |
| <span class="kn">from</span> <span class="nn">airflow</span> <span class="kn">import</span> <span class="n">models</span> |
| <span class="kn">from</span> <span class="nn">airflow.contrib.hooks.gcp_transfer_hook</span> <span class="kn">import</span> <span class="p">(</span> |
| <span class="n">GcpTransferOperationStatus</span><span class="p">,</span> |
| <span class="n">GcpTransferJobsStatus</span><span class="p">,</span> |
| <span class="n">TRANSFER_OPTIONS</span><span class="p">,</span> |
| <span class="n">PROJECT_ID</span><span class="p">,</span> |
| <span class="n">BUCKET_NAME</span><span class="p">,</span> |
| <span class="n">GCS_DATA_SINK</span><span class="p">,</span> |
| <span class="n">STATUS</span><span class="p">,</span> |
| <span class="n">DESCRIPTION</span><span class="p">,</span> |
| <span class="n">GCS_DATA_SOURCE</span><span class="p">,</span> |
| <span class="n">START_TIME_OF_DAY</span><span class="p">,</span> |
| <span class="n">SCHEDULE_END_DATE</span><span class="p">,</span> |
| <span class="n">SCHEDULE_START_DATE</span><span class="p">,</span> |
| <span class="n">SCHEDULE</span><span class="p">,</span> |
| <span class="n">AWS_S3_DATA_SOURCE</span><span class="p">,</span> |
| <span class="n">TRANSFER_SPEC</span><span class="p">,</span> |
| <span class="n">FILTER_PROJECT_ID</span><span class="p">,</span> |
| <span class="n">FILTER_JOB_NAMES</span><span class="p">,</span> |
| <span class="n">TRANSFER_JOB</span><span class="p">,</span> |
| <span class="n">TRANSFER_JOB_FIELD_MASK</span><span class="p">,</span> |
| <span class="n">ALREADY_EXISTING_IN_SINK</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="kn">from</span> <span class="nn">airflow.contrib.operators.gcp_transfer_operator</span> <span class="kn">import</span> <span class="p">(</span> |
| <span class="n">GcpTransferServiceJobCreateOperator</span><span class="p">,</span> |
| <span class="n">GcpTransferServiceJobDeleteOperator</span><span class="p">,</span> |
| <span class="n">GcpTransferServiceJobUpdateOperator</span><span class="p">,</span> |
| <span class="n">GcpTransferServiceOperationsListOperator</span><span class="p">,</span> |
| <span class="n">GcpTransferServiceOperationGetOperator</span><span class="p">,</span> |
| <span class="n">GcpTransferServiceOperationPauseOperator</span><span class="p">,</span> |
| <span class="n">GcpTransferServiceOperationResumeOperator</span><span class="p">,</span> |
| <span class="n">GcpTransferServiceOperationCancelOperator</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="kn">from</span> <span class="nn">airflow.contrib.sensors.gcp_transfer_sensor</span> <span class="kn">import</span> <span class="n">GCPTransferServiceWaitForJobStatusSensor</span> |
| <span class="kn">from</span> <span class="nn">airflow.utils.dates</span> <span class="kn">import</span> <span class="n">days_ago</span> |
| |
| <span class="c1"># [START howto_operator_gcp_transfer_common_variables]</span> |
| <span class="n">GCP_PROJECT_ID</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'GCP_PROJECT_ID'</span><span class="p">,</span> <span class="s1">'example-project'</span><span class="p">)</span> |
| <span class="n">GCP_DESCRIPTION</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'GCP_DESCRIPTION'</span><span class="p">,</span> <span class="s1">'description'</span><span class="p">)</span> |
| <span class="n">GCP_TRANSFER_TARGET_BUCKET</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'GCP_TRANSFER_TARGET_BUCKET'</span><span class="p">)</span> |
| <span class="n">WAIT_FOR_OPERATION_POKE_INTERVAL</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'WAIT_FOR_OPERATION_POKE_INTERVAL'</span><span class="p">,</span> <span class="mi">5</span><span class="p">))</span> |
| |
| <span class="n">GCP_TRANSFER_SOURCE_AWS_BUCKET</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'GCP_TRANSFER_SOURCE_AWS_BUCKET'</span><span class="p">)</span> |
| <span class="n">GCP_TRANSFER_FIRST_TARGET_BUCKET</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="o">.</span><span class="n">get</span><span class="p">(</span> |
| <span class="s1">'GCP_TRANSFER_FIRST_TARGET_BUCKET'</span><span class="p">,</span> <span class="s1">'gcp-transfer-first-target'</span> |
| <span class="p">)</span> |
| <span class="n">GCP_TRANSFER_SECOND_TARGET_BUCKET</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="o">.</span><span class="n">get</span><span class="p">(</span> |
| <span class="s1">'GCP_TRANSFER_SECOND_TARGET_BUCKET'</span><span class="p">,</span> <span class="s1">'gcp-transfer-second-target'</span> |
| <span class="p">)</span> |
| <span class="c1"># [END howto_operator_gcp_transfer_common_variables]</span> |
| |
| <span class="c1"># [START howto_operator_gcp_transfer_create_job_body_aws]</span> |
| <span class="n">aws_to_gcs_transfer_body</span> <span class="o">=</span> <span class="p">{</span> |
| <span class="n">DESCRIPTION</span><span class="p">:</span> <span class="n">GCP_DESCRIPTION</span><span class="p">,</span> |
| <span class="n">STATUS</span><span class="p">:</span> <span class="n">GcpTransferJobsStatus</span><span class="o">.</span><span class="n">ENABLED</span><span class="p">,</span> |
| <span class="n">PROJECT_ID</span><span class="p">:</span> <span class="n">GCP_PROJECT_ID</span><span class="p">,</span> |
| <span class="n">SCHEDULE</span><span class="p">:</span> <span class="p">{</span> |
| <span class="n">SCHEDULE_START_DATE</span><span class="p">:</span> <span class="n">datetime</span><span class="p">(</span><span class="mi">2015</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span><span class="o">.</span><span class="n">date</span><span class="p">(),</span> |
| <span class="n">SCHEDULE_END_DATE</span><span class="p">:</span> <span class="n">datetime</span><span class="p">(</span><span class="mi">2030</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span><span class="o">.</span><span class="n">date</span><span class="p">(),</span> |
| <span class="n">START_TIME_OF_DAY</span><span class="p">:</span> <span class="p">(</span><span class="n">datetime</span><span class="o">.</span><span class="n">utcnow</span><span class="p">()</span> <span class="o">+</span> <span class="n">timedelta</span><span class="p">(</span><span class="n">minutes</span><span class="o">=</span><span class="mi">2</span><span class="p">))</span><span class="o">.</span><span class="n">time</span><span class="p">(),</span> |
| <span class="p">},</span> |
| <span class="n">TRANSFER_SPEC</span><span class="p">:</span> <span class="p">{</span> |
| <span class="n">AWS_S3_DATA_SOURCE</span><span class="p">:</span> <span class="p">{</span><span class="n">BUCKET_NAME</span><span class="p">:</span> <span class="n">GCP_TRANSFER_SOURCE_AWS_BUCKET</span><span class="p">},</span> |
| <span class="n">GCS_DATA_SINK</span><span class="p">:</span> <span class="p">{</span><span class="n">BUCKET_NAME</span><span class="p">:</span> <span class="n">GCP_TRANSFER_FIRST_TARGET_BUCKET</span><span class="p">},</span> |
| <span class="n">TRANSFER_OPTIONS</span><span class="p">:</span> <span class="p">{</span><span class="n">ALREADY_EXISTING_IN_SINK</span><span class="p">:</span> <span class="kc">True</span><span class="p">},</span> |
| <span class="p">},</span> |
| <span class="p">}</span> |
| <span class="c1"># [END howto_operator_gcp_transfer_create_job_body_aws]</span> |
| |
| <span class="c1"># [START howto_operator_gcp_transfer_create_job_body_gcp]</span> |
| <span class="n">gcs_to_gcs_transfer_body</span> <span class="o">=</span> <span class="p">{</span> |
| <span class="n">DESCRIPTION</span><span class="p">:</span> <span class="n">GCP_DESCRIPTION</span><span class="p">,</span> |
| <span class="n">STATUS</span><span class="p">:</span> <span class="n">GcpTransferJobsStatus</span><span class="o">.</span><span class="n">ENABLED</span><span class="p">,</span> |
| <span class="n">PROJECT_ID</span><span class="p">:</span> <span class="n">GCP_PROJECT_ID</span><span class="p">,</span> |
| <span class="n">SCHEDULE</span><span class="p">:</span> <span class="p">{</span> |
| <span class="n">SCHEDULE_START_DATE</span><span class="p">:</span> <span class="n">datetime</span><span class="p">(</span><span class="mi">2015</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span><span class="o">.</span><span class="n">date</span><span class="p">(),</span> |
| <span class="n">SCHEDULE_END_DATE</span><span class="p">:</span> <span class="n">datetime</span><span class="p">(</span><span class="mi">2030</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span><span class="o">.</span><span class="n">date</span><span class="p">(),</span> |
| <span class="n">START_TIME_OF_DAY</span><span class="p">:</span> <span class="p">(</span><span class="n">datetime</span><span class="o">.</span><span class="n">utcnow</span><span class="p">()</span> <span class="o">+</span> <span class="n">timedelta</span><span class="p">(</span><span class="n">minutes</span><span class="o">=</span><span class="mi">2</span><span class="p">))</span><span class="o">.</span><span class="n">time</span><span class="p">(),</span> |
| <span class="p">},</span> |
| <span class="n">TRANSFER_SPEC</span><span class="p">:</span> <span class="p">{</span> |
| <span class="n">GCS_DATA_SOURCE</span><span class="p">:</span> <span class="p">{</span><span class="n">BUCKET_NAME</span><span class="p">:</span> <span class="n">GCP_TRANSFER_FIRST_TARGET_BUCKET</span><span class="p">},</span> |
| <span class="n">GCS_DATA_SINK</span><span class="p">:</span> <span class="p">{</span><span class="n">BUCKET_NAME</span><span class="p">:</span> <span class="n">GCP_TRANSFER_SECOND_TARGET_BUCKET</span><span class="p">},</span> |
| <span class="n">TRANSFER_OPTIONS</span><span class="p">:</span> <span class="p">{</span><span class="n">ALREADY_EXISTING_IN_SINK</span><span class="p">:</span> <span class="kc">True</span><span class="p">},</span> |
| <span class="p">},</span> |
| <span class="p">}</span> <span class="c1"># type: Dict[str, Any]</span> |
| <span class="c1"># [END howto_operator_gcp_transfer_create_job_body_gcp]</span> |
| |
| <span class="c1"># [START howto_operator_gcp_transfer_update_job_body]</span> |
| <span class="n">update_body</span> <span class="o">=</span> <span class="p">{</span> |
| <span class="n">PROJECT_ID</span><span class="p">:</span> <span class="n">GCP_PROJECT_ID</span><span class="p">,</span> |
| <span class="n">TRANSFER_JOB</span><span class="p">:</span> <span class="p">{</span><span class="n">DESCRIPTION</span><span class="p">:</span> <span class="s2">"</span><span class="si">{}</span><span class="s2">_updated"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">GCP_DESCRIPTION</span><span class="p">)},</span> |
| <span class="n">TRANSFER_JOB_FIELD_MASK</span><span class="p">:</span> <span class="s2">"description"</span><span class="p">,</span> |
| <span class="p">}</span> |
| <span class="c1"># [END howto_operator_gcp_transfer_update_job_body]</span> |
| |
| <span class="n">list_filter_dict</span> <span class="o">=</span> <span class="p">{</span><span class="n">FILTER_PROJECT_ID</span><span class="p">:</span> <span class="n">GCP_PROJECT_ID</span><span class="p">,</span> <span class="n">FILTER_JOB_NAMES</span><span class="p">:</span> <span class="p">[]}</span> |
| |
| <span class="c1"># [START howto_operator_gcp_transfer_default_args]</span> |
| <span class="n">default_args</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'start_date'</span><span class="p">:</span> <span class="n">days_ago</span><span class="p">(</span><span class="mi">1</span><span class="p">)}</span> |
| <span class="c1"># [END howto_operator_gcp_transfer_default_args]</span> |
| |
| <span class="k">with</span> <span class="n">models</span><span class="o">.</span><span class="n">DAG</span><span class="p">(</span> |
| <span class="s1">'example_gcp_transfer'</span><span class="p">,</span> <span class="n">default_args</span><span class="o">=</span><span class="n">default_args</span><span class="p">,</span> <span class="n">schedule_interval</span><span class="o">=</span><span class="kc">None</span> <span class="c1"># Override to match your needs</span> |
| <span class="p">)</span> <span class="k">as</span> <span class="n">dag</span><span class="p">:</span> |
| |
| <span class="c1"># [START howto_operator_gcp_transfer_create_job]</span> |
| <span class="n">create_transfer_job_from_aws</span> <span class="o">=</span> <span class="n">GcpTransferServiceJobCreateOperator</span><span class="p">(</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s2">"create_transfer_job_from_aws"</span><span class="p">,</span> <span class="n">body</span><span class="o">=</span><span class="n">aws_to_gcs_transfer_body</span> |
| <span class="p">)</span> |
| <span class="c1"># [END howto_operator_gcp_transfer_create_job]</span> |
| |
| <span class="n">wait_for_operation_to_start</span> <span class="o">=</span> <span class="n">GCPTransferServiceWaitForJobStatusSensor</span><span class="p">(</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s2">"wait_for_operation_to_start"</span><span class="p">,</span> |
| <span class="n">job_name</span><span class="o">=</span><span class="s2">"{{task_instance.xcom_pull('create_transfer_job_from_aws')['name']}}"</span><span class="p">,</span> |
| <span class="n">project_id</span><span class="o">=</span><span class="n">GCP_PROJECT_ID</span><span class="p">,</span> |
| <span class="n">expected_statuses</span><span class="o">=</span><span class="p">{</span><span class="n">GcpTransferOperationStatus</span><span class="o">.</span><span class="n">IN_PROGRESS</span><span class="p">},</span> |
| <span class="n">poke_interval</span><span class="o">=</span><span class="n">WAIT_FOR_OPERATION_POKE_INTERVAL</span><span class="p">,</span> |
| <span class="p">)</span> |
| |
| <span class="c1"># [START howto_operator_gcp_transfer_pause_operation]</span> |
| <span class="n">pause_operation</span> <span class="o">=</span> <span class="n">GcpTransferServiceOperationPauseOperator</span><span class="p">(</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s2">"pause_operation"</span><span class="p">,</span> |
| <span class="n">operation_name</span><span class="o">=</span><span class="s2">"{{task_instance.xcom_pull('wait_for_operation_to_start', "</span> |
| <span class="s2">"key='sensed_operations')[0]['name']}}"</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="c1"># [END howto_operator_gcp_transfer_pause_operation]</span> |
| |
| <span class="c1"># [START howto_operator_gcp_transfer_update_job]</span> |
| <span class="n">update_job</span> <span class="o">=</span> <span class="n">GcpTransferServiceJobUpdateOperator</span><span class="p">(</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s2">"update_job"</span><span class="p">,</span> |
| <span class="n">job_name</span><span class="o">=</span><span class="s2">"{{task_instance.xcom_pull('create_transfer_job_from_aws')['name']}}"</span><span class="p">,</span> |
| <span class="n">body</span><span class="o">=</span><span class="n">update_body</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="c1"># [END howto_operator_gcp_transfer_update_job]</span> |
| |
| <span class="c1"># [START howto_operator_gcp_transfer_list_operations]</span> |
| <span class="n">list_operations</span> <span class="o">=</span> <span class="n">GcpTransferServiceOperationsListOperator</span><span class="p">(</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s2">"list_operations"</span><span class="p">,</span> |
| <span class="nb">filter</span><span class="o">=</span><span class="p">{</span> |
| <span class="n">FILTER_PROJECT_ID</span><span class="p">:</span> <span class="n">GCP_PROJECT_ID</span><span class="p">,</span> |
| <span class="n">FILTER_JOB_NAMES</span><span class="p">:</span> <span class="p">[</span><span class="s2">"{{task_instance.xcom_pull('create_transfer_job_from_aws')['name']}}"</span><span class="p">],</span> |
| <span class="p">},</span> |
| <span class="p">)</span> |
| <span class="c1"># [END howto_operator_gcp_transfer_list_operations]</span> |
| |
| <span class="c1"># [START howto_operator_gcp_transfer_get_operation]</span> |
| <span class="n">get_operation</span> <span class="o">=</span> <span class="n">GcpTransferServiceOperationGetOperator</span><span class="p">(</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s2">"get_operation"</span><span class="p">,</span> <span class="n">operation_name</span><span class="o">=</span><span class="s2">"{{task_instance.xcom_pull('list_operations')[0]['name']}}"</span> |
| <span class="p">)</span> |
| <span class="c1"># [END howto_operator_gcp_transfer_get_operation]</span> |
| |
| <span class="c1"># [START howto_operator_gcp_transfer_resume_operation]</span> |
| <span class="n">resume_operation</span> <span class="o">=</span> <span class="n">GcpTransferServiceOperationResumeOperator</span><span class="p">(</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s2">"resume_operation"</span><span class="p">,</span> <span class="n">operation_name</span><span class="o">=</span><span class="s2">"{{task_instance.xcom_pull('get_operation')['name']}}"</span> |
| <span class="p">)</span> |
| <span class="c1"># [END howto_operator_gcp_transfer_resume_operation]</span> |
| |
| <span class="c1"># [START howto_operator_gcp_transfer_wait_operation]</span> |
| <span class="n">wait_for_operation_to_end</span> <span class="o">=</span> <span class="n">GCPTransferServiceWaitForJobStatusSensor</span><span class="p">(</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s2">"wait_for_operation_to_end"</span><span class="p">,</span> |
| <span class="n">job_name</span><span class="o">=</span><span class="s2">"{{task_instance.xcom_pull('create_transfer_job_from_aws')['name']}}"</span><span class="p">,</span> |
| <span class="n">project_id</span><span class="o">=</span><span class="n">GCP_PROJECT_ID</span><span class="p">,</span> |
| <span class="n">expected_statuses</span><span class="o">=</span><span class="p">{</span><span class="n">GcpTransferOperationStatus</span><span class="o">.</span><span class="n">SUCCESS</span><span class="p">},</span> |
| <span class="n">poke_interval</span><span class="o">=</span><span class="n">WAIT_FOR_OPERATION_POKE_INTERVAL</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="c1"># [END howto_operator_gcp_transfer_wait_operation]</span> |
| |
| <span class="n">job_time</span> <span class="o">=</span> <span class="n">datetime</span><span class="o">.</span><span class="n">utcnow</span><span class="p">()</span> <span class="o">+</span> <span class="n">timedelta</span><span class="p">(</span><span class="n">minutes</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span> |
| |
| <span class="n">gcs_to_gcs_transfer_body</span><span class="p">[</span><span class="s1">'schedule'</span><span class="p">][</span><span class="s1">'startTimeOfDay'</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span><span class="n">datetime</span><span class="o">.</span><span class="n">utcnow</span><span class="p">()</span> <span class="o">+</span> <span class="n">timedelta</span><span class="p">(</span><span class="n">minutes</span><span class="o">=</span><span class="mi">2</span><span class="p">))</span><span class="o">.</span><span class="n">time</span><span class="p">()</span> |
| |
| <span class="n">create_transfer_job_from_gcp</span> <span class="o">=</span> <span class="n">GcpTransferServiceJobCreateOperator</span><span class="p">(</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s2">"create_transfer_job_from_gcp"</span><span class="p">,</span> <span class="n">body</span><span class="o">=</span><span class="n">gcs_to_gcs_transfer_body</span> |
| <span class="p">)</span> |
| |
| <span class="n">wait_for_second_operation_to_start</span> <span class="o">=</span> <span class="n">GCPTransferServiceWaitForJobStatusSensor</span><span class="p">(</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s2">"wait_for_second_operation_to_start"</span><span class="p">,</span> |
| <span class="n">job_name</span><span class="o">=</span><span class="s2">"{{ task_instance.xcom_pull('create_transfer_job_from_gcp')['name'] }}"</span><span class="p">,</span> |
| <span class="n">project_id</span><span class="o">=</span><span class="n">GCP_PROJECT_ID</span><span class="p">,</span> |
| <span class="n">expected_statuses</span><span class="o">=</span><span class="p">{</span><span class="n">GcpTransferOperationStatus</span><span class="o">.</span><span class="n">IN_PROGRESS</span><span class="p">},</span> |
| <span class="n">poke_interval</span><span class="o">=</span><span class="n">WAIT_FOR_OPERATION_POKE_INTERVAL</span><span class="p">,</span> |
| <span class="p">)</span> |
| |
| <span class="c1"># [START howto_operator_gcp_transfer_cancel_operation]</span> |
| <span class="n">cancel_operation</span> <span class="o">=</span> <span class="n">GcpTransferServiceOperationCancelOperator</span><span class="p">(</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s2">"cancel_operation"</span><span class="p">,</span> |
| <span class="n">operation_name</span><span class="o">=</span><span class="s2">"{{task_instance.xcom_pull("</span> |
| <span class="s2">"'wait_for_second_operation_to_start', key='sensed_operations')[0]['name']}}"</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="c1"># [END howto_operator_gcp_transfer_cancel_operation]</span> |
| |
| <span class="c1"># [START howto_operator_gcp_transfer_delete_job]</span> |
| <span class="n">delete_transfer_from_aws_job</span> <span class="o">=</span> <span class="n">GcpTransferServiceJobDeleteOperator</span><span class="p">(</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s2">"delete_transfer_from_aws_job"</span><span class="p">,</span> |
| <span class="n">job_name</span><span class="o">=</span><span class="s2">"{{task_instance.xcom_pull('create_transfer_job_from_aws')['name']}}"</span><span class="p">,</span> |
| <span class="n">project_id</span><span class="o">=</span><span class="n">GCP_PROJECT_ID</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="c1"># [END howto_operator_gcp_transfer_delete_job]</span> |
| |
| <span class="n">delete_transfer_from_gcp_job</span> <span class="o">=</span> <span class="n">GcpTransferServiceJobDeleteOperator</span><span class="p">(</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s2">"delete_transfer_from_gcp_job"</span><span class="p">,</span> |
| <span class="n">job_name</span><span class="o">=</span><span class="s2">"{{task_instance.xcom_pull('create_transfer_job_from_gcp')['name']}}"</span><span class="p">,</span> |
| <span class="n">project_id</span><span class="o">=</span><span class="n">GCP_PROJECT_ID</span><span class="p">,</span> |
| <span class="p">)</span> |
| |
| <span class="n">create_transfer_job_from_aws</span> <span class="o">>></span> <span class="n">wait_for_operation_to_start</span> <span class="o">>></span> <span class="n">pause_operation</span> <span class="o">>></span> \ |
| <span class="n">list_operations</span> <span class="o">>></span> <span class="n">get_operation</span> <span class="o">>></span> <span class="n">resume_operation</span> <span class="o">>></span> <span class="n">wait_for_operation_to_end</span> <span class="o">>></span> \ |
| <span class="n">create_transfer_job_from_gcp</span> <span class="o">>></span> <span class="n">wait_for_second_operation_to_start</span> <span class="o">>></span> <span class="n">cancel_operation</span> <span class="o">>></span> \ |
| <span class="n">delete_transfer_from_aws_job</span> <span class="o">>></span> <span class="n">delete_transfer_from_gcp_job</span> |
| </pre></div> |
| |
| </div> |
| |
| </div> |
| |
| |
| <footer> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| |
| </p> |
| </div> |
| Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| <div class="footer">This page uses <a href="https://analytics.google.com/"> |
| Google Analytics</a> to collect statistics. You can disable it by blocking |
| the JavaScript coming from www.google-analytics.com. Check our |
| <a href="../../../../privacy_notice.html">Privacy Policy</a> |
| for more details. |
| </div> |
| |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| |
| |
| |
| <!-- Theme Analytics --> |
| <script> |
| (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ |
| (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o), |
| m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) |
| })(window,document,'script','https://www.google-analytics.com/analytics.js','ga'); |
| |
| ga('create', 'UA-140539454-1', 'auto'); |
| ga('send', 'pageview'); |
| </script> |
| |
| |
| |
| |
| </body> |
| </html> |