blob: 19afeeaa5ae35127257cbf74b0a22c9d8b3edb98 [file] [log] [blame]
<!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.operators.s3_to_gcs_transfer_operator &mdash; Airflow Documentation</title>
<link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
<link rel="index" title="Index" href="../../../../genindex.html" />
<link rel="search" title="Search" href="../../../../search.html" />
<script src="../../../../_static/js/modernizr.min.js"></script>
</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">
1.10.2
</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</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling &amp; Triggers</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">Experimental Rest API</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="../../../../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="../../../../changelog.html">Changelog</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="../../../../code.html">API Reference</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> &raquo;</li>
<li><a href="../../../index.html">Module code</a> &raquo;</li>
<li>airflow.contrib.operators.s3_to_gcs_transfer_operator</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.operators.s3_to_gcs_transfer_operator</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"># &quot;License&quot;); 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"># &quot;AS IS&quot; 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="kn">from</span> <span class="nn">airflow.models</span> <span class="k">import</span> <span class="n">BaseOperator</span>
<span class="kn">from</span> <span class="nn">airflow.hooks.S3_hook</span> <span class="k">import</span> <span class="n">S3Hook</span>
<span class="kn">from</span> <span class="nn">airflow.contrib.hooks.gcp_transfer_hook</span> <span class="k">import</span> <span class="n">GCPTransferServiceHook</span>
<span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="k">import</span> <span class="n">apply_defaults</span>
<div class="viewcode-block" id="S3ToGoogleCloudStorageTransferOperator"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.operators.s3_to_gcs_transfer_operator.S3ToGoogleCloudStorageTransferOperator">[docs]</a><span class="k">class</span> <span class="nc">S3ToGoogleCloudStorageTransferOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Synchronizes an S3 bucket with a Google Cloud Storage bucket using the</span>
<span class="sd"> GCP Storage Transfer Service.</span>
<span class="sd"> :param s3_bucket: The S3 bucket where to find the objects. (templated)</span>
<span class="sd"> :type s3_bucket: str</span>
<span class="sd"> :param gcs_bucket: The destination Google Cloud Storage bucket</span>
<span class="sd"> where you want to store the files. (templated)</span>
<span class="sd"> :type gcs_bucket: str</span>
<span class="sd"> :param project_id: Optional ID of the Google Cloud Platform Console project that</span>
<span class="sd"> owns the job</span>
<span class="sd"> :type project_id: str</span>
<span class="sd"> :param aws_conn_id: The source S3 connection</span>
<span class="sd"> :type aws_conn_id: str</span>
<span class="sd"> :param gcp_conn_id: The destination connection ID to use</span>
<span class="sd"> when connecting to Google Cloud Storage.</span>
<span class="sd"> :type gcp_conn_id: str</span>
<span class="sd"> :param delegate_to: The account to impersonate, if any.</span>
<span class="sd"> For this to work, the service account making the request must have</span>
<span class="sd"> domain-wide delegation enabled.</span>
<span class="sd"> :type delegate_to: str</span>
<span class="sd"> :param description: Optional transfer service job description</span>
<span class="sd"> :type description: str</span>
<span class="sd"> :param schedule: Optional transfer service schedule; see</span>
<span class="sd"> https://cloud.google.com/storage-transfer/docs/reference/rest/v1/transferJobs.</span>
<span class="sd"> If not set, run transfer job once as soon as the operator runs</span>
<span class="sd"> :type schedule: dict</span>
<span class="sd"> :param object_conditions: Optional transfer service object conditions; see</span>
<span class="sd"> https://cloud.google.com/storage-transfer/docs/reference/rest/v1/TransferSpec</span>
<span class="sd"> :type object_conditions: dict</span>
<span class="sd"> :param transfer_options: Optional transfer service transfer options; see</span>
<span class="sd"> https://cloud.google.com/storage-transfer/docs/reference/rest/v1/TransferSpec</span>
<span class="sd"> :type transfer_options: dict</span>
<span class="sd"> :param wait: Wait for transfer to finish</span>
<span class="sd"> :type wait: bool</span>
<span class="sd"> **Example**:</span>
<span class="sd"> .. code-block:: python</span>
<span class="sd"> s3_to_gcs_transfer_op = S3ToGoogleCloudStorageTransferOperator(</span>
<span class="sd"> task_id=&#39;s3_to_gcs_transfer_example&#39;,</span>
<span class="sd"> s3_bucket=&#39;my-s3-bucket&#39;,</span>
<span class="sd"> project_id=&#39;my-gcp-project&#39;,</span>
<span class="sd"> gcs_bucket=&#39;my-gcs-bucket&#39;,</span>
<span class="sd"> dag=my_dag)</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;s3_bucket&#39;</span><span class="p">,</span> <span class="s1">&#39;gcs_bucket&#39;</span><span class="p">,</span> <span class="s1">&#39;description&#39;</span><span class="p">,</span> <span class="s1">&#39;object_conditions&#39;</span><span class="p">)</span>
<span class="n">ui_color</span> <span class="o">=</span> <span class="s1">&#39;#e09411&#39;</span>
<span class="nd">@apply_defaults</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span>
<span class="n">s3_bucket</span><span class="p">,</span>
<span class="n">gcs_bucket</span><span class="p">,</span>
<span class="n">project_id</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">aws_conn_id</span><span class="o">=</span><span class="s1">&#39;aws_default&#39;</span><span class="p">,</span>
<span class="n">gcp_conn_id</span><span class="o">=</span><span class="s1">&#39;google_cloud_default&#39;</span><span class="p">,</span>
<span class="n">delegate_to</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">description</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">schedule</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">object_conditions</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">transfer_options</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">wait</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="o">*</span><span class="n">args</span><span class="p">,</span>
<span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">S3ToGoogleCloudStorageTransferOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span>
<span class="o">*</span><span class="n">args</span><span class="p">,</span>
<span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">s3_bucket</span> <span class="o">=</span> <span class="n">s3_bucket</span>
<span class="bp">self</span><span class="o">.</span><span class="n">gcs_bucket</span> <span class="o">=</span> <span class="n">gcs_bucket</span>
<span class="bp">self</span><span class="o">.</span><span class="n">project_id</span> <span class="o">=</span> <span class="n">project_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">aws_conn_id</span> <span class="o">=</span> <span class="n">aws_conn_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span> <span class="o">=</span> <span class="n">gcp_conn_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span> <span class="o">=</span> <span class="n">delegate_to</span>
<span class="bp">self</span><span class="o">.</span><span class="n">description</span> <span class="o">=</span> <span class="n">description</span>
<span class="bp">self</span><span class="o">.</span><span class="n">schedule</span> <span class="o">=</span> <span class="n">schedule</span>
<span class="bp">self</span><span class="o">.</span><span class="n">object_conditions</span> <span class="o">=</span> <span class="n">object_conditions</span> <span class="ow">or</span> <span class="p">{}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">transfer_options</span> <span class="o">=</span> <span class="n">transfer_options</span> <span class="ow">or</span> <span class="p">{}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">wait</span> <span class="o">=</span> <span class="n">wait</span>
<span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span>
<span class="n">transfer_hook</span> <span class="o">=</span> <span class="n">GCPTransferServiceHook</span><span class="p">(</span>
<span class="n">gcp_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span><span class="p">,</span>
<span class="n">delegate_to</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span><span class="p">)</span>
<span class="n">s3_creds</span> <span class="o">=</span> <span class="n">S3Hook</span><span class="p">(</span><span class="n">aws_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">aws_conn_id</span><span class="p">)</span><span class="o">.</span><span class="n">get_credentials</span><span class="p">()</span>
<span class="n">job</span> <span class="o">=</span> <span class="n">transfer_hook</span><span class="o">.</span><span class="n">create_transfer_job</span><span class="p">(</span>
<span class="n">project_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">project_id</span><span class="p">,</span>
<span class="n">description</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">description</span><span class="p">,</span>
<span class="n">schedule</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">schedule</span><span class="p">,</span>
<span class="n">transfer_spec</span><span class="o">=</span><span class="p">{</span>
<span class="s1">&#39;awsS3DataSource&#39;</span><span class="p">:</span> <span class="p">{</span>
<span class="s1">&#39;bucketName&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">s3_bucket</span><span class="p">,</span>
<span class="s1">&#39;awsAccessKey&#39;</span><span class="p">:</span> <span class="p">{</span>
<span class="s1">&#39;accessKeyId&#39;</span><span class="p">:</span> <span class="n">s3_creds</span><span class="o">.</span><span class="n">access_key</span><span class="p">,</span>
<span class="s1">&#39;secretAccessKey&#39;</span><span class="p">:</span> <span class="n">s3_creds</span><span class="o">.</span><span class="n">secret_key</span><span class="p">,</span>
<span class="p">}</span>
<span class="p">},</span>
<span class="s1">&#39;gcsDataSink&#39;</span><span class="p">:</span> <span class="p">{</span>
<span class="s1">&#39;bucketName&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">gcs_bucket</span><span class="p">,</span>
<span class="p">},</span>
<span class="s1">&#39;objectConditions&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">object_conditions</span><span class="p">,</span>
<span class="s1">&#39;transferOptions&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">transfer_options</span><span class="p">,</span>
<span class="p">}</span>
<span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">wait</span><span class="p">:</span>
<span class="n">transfer_hook</span><span class="o">.</span><span class="n">wait_for_transfer_job</span><span class="p">(</span><span class="n">job</span><span class="p">)</span></div>
</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>.
</footer>
</div>
</div>
</section>
</div>
<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/js/theme.js"></script>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>