blob: 65db58b5dd90893000792e6510dee3539e300cc6 [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.adls_to_gcs &mdash; Airflow Documentation</title>
<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/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="index" title="Index" href="../../../../genindex.html" />
<link rel="search" title="Search" href="../../../../search.html" />
<script>
document.addEventListener('DOMContentLoaded', function() {
var el = document.getElementById('changelog');
if (el !== null ) {
// [AIRFLOW-...]
el.innerHTML = el.innerHTML.replace(
/\[(AIRFLOW-[\d]+)\]/g,
`<a href="https://issues.apache.org/jira/browse/$1">[$1]</a>`
);
// (#...)
el.innerHTML = el.innerHTML.replace(
/\(#([\d]+)\)/g,
`<a href="https://github.com/apache/airflow/pull/$1">(#$1)</a>`
);
};
})
</script>
<style>
.example-header {
position: relative;
background: #9AAA7A;
padding: 8px 16px;
margin-bottom: 0;
}
.example-header--with-button {
padding-right: 166px;
}
.example-header:after{
content: '';
display: table;
clear: both;
}
.example-title {
display:block;
padding: 4px;
margin-right: 16px;
color: white;
overflow-x: auto;
}
.example-header-button {
top: 8px;
right: 16px;
position: absolute;
}
.example-header + .highlight-python {
margin-top: 0 !important;
}
.viewcode-button {
display: inline-block;
padding: 8px 16px;
border: 0;
margin: 0;
outline: 0;
border-radius: 2px;
-webkit-box-shadow: 0 3px 5px 0 rgba(0,0,0,.3);
box-shadow: 0 3px 6px 0 rgba(0,0,0,.3);
color: #404040;
background-color: #e7e7e7;
cursor: pointer;
font-size: 16px;
font-weight: 500;
line-height: 1;
text-decoration: none;
text-overflow: ellipsis;
overflow: hidden;
text-transform: uppercase;
-webkit-transition: background-color .2s;
transition: background-color .2s;
vertical-align: middle;
white-space: nowrap;
}
.viewcode-button:visited {
color: #404040;
}
.viewcode-button:hover, .viewcode-button:focus {
color: #404040;
background-color: #d6d6d6;
}
</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">
1.10.4
</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="../../../../macros.html">Macros reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../_api/index.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><a href="../operators.html">airflow.contrib.operators</a> &raquo;</li>
<li>airflow.contrib.operators.adls_to_gcs</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.adls_to_gcs</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">import</span> <span class="nn">os</span>
<span class="kn">from</span> <span class="nn">tempfile</span> <span class="k">import</span> <span class="n">NamedTemporaryFile</span>
<span class="kn">from</span> <span class="nn">airflow.contrib.hooks.azure_data_lake_hook</span> <span class="k">import</span> <span class="n">AzureDataLakeHook</span>
<span class="kn">from</span> <span class="nn">airflow.contrib.operators.adls_list_operator</span> <span class="k">import</span> <span class="n">AzureDataLakeStorageListOperator</span>
<span class="kn">from</span> <span class="nn">airflow.contrib.hooks.gcs_hook</span> <span class="k">import</span> <span class="n">GoogleCloudStorageHook</span><span class="p">,</span> <span class="n">_parse_gcs_url</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="AdlsToGoogleCloudStorageOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/adls_to_gcs/index.html#airflow.contrib.operators.adls_to_gcs.AdlsToGoogleCloudStorageOperator">[docs]</a><span class="k">class</span> <span class="nc">AdlsToGoogleCloudStorageOperator</span><span class="p">(</span><span class="n">AzureDataLakeStorageListOperator</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Synchronizes an Azure Data Lake Storage path with a GCS bucket</span>
<span class="sd"> :param src_adls: The Azure Data Lake path to find the objects (templated)</span>
<span class="sd"> :type src_adls: str</span>
<span class="sd"> :param dest_gcs: The Google Cloud Storage bucket and prefix to</span>
<span class="sd"> store the objects. (templated)</span>
<span class="sd"> :type dest_gcs: str</span>
<span class="sd"> :param replace: If true, replaces same-named files in GCS</span>
<span class="sd"> :type replace: bool</span>
<span class="sd"> :param azure_data_lake_conn_id: The connection ID to use when</span>
<span class="sd"> connecting to Azure Data Lake Storage.</span>
<span class="sd"> :type azure_data_lake_conn_id: str</span>
<span class="sd"> :param google_cloud_storage_conn_id: The connection ID to use when</span>
<span class="sd"> connecting to Google Cloud Storage.</span>
<span class="sd"> :type google_cloud_storage_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"> **Examples**:</span>
<span class="sd"> The following Operator would copy a single file named</span>
<span class="sd"> ``hello/world.avro`` from ADLS to the GCS bucket ``mybucket``. Its full</span>
<span class="sd"> resulting gcs path will be ``gs://mybucket/hello/world.avro`` ::</span>
<span class="sd"> copy_single_file = AdlsToGoogleCloudStorageOperator(</span>
<span class="sd"> task_id=&#39;copy_single_file&#39;,</span>
<span class="sd"> src_adls=&#39;hello/world.avro&#39;,</span>
<span class="sd"> dest_gcs=&#39;gs://mybucket&#39;,</span>
<span class="sd"> replace=False,</span>
<span class="sd"> azure_data_lake_conn_id=&#39;azure_data_lake_default&#39;,</span>
<span class="sd"> google_cloud_storage_conn_id=&#39;google_cloud_default&#39;</span>
<span class="sd"> )</span>
<span class="sd"> The following Operator would copy all parquet files from ADLS</span>
<span class="sd"> to the GCS bucket ``mybucket``. ::</span>
<span class="sd"> copy_all_files = AdlsToGoogleCloudStorageOperator(</span>
<span class="sd"> task_id=&#39;copy_all_files&#39;,</span>
<span class="sd"> src_adls=&#39;*.parquet&#39;,</span>
<span class="sd"> dest_gcs=&#39;gs://mybucket&#39;,</span>
<span class="sd"> replace=False,</span>
<span class="sd"> azure_data_lake_conn_id=&#39;azure_data_lake_default&#39;,</span>
<span class="sd"> google_cloud_storage_conn_id=&#39;google_cloud_default&#39;</span>
<span class="sd"> )</span>
<span class="sd"> The following Operator would copy all parquet files from ADLS</span>
<span class="sd"> path ``/hello/world``to the GCS bucket ``mybucket``. ::</span>
<span class="sd"> copy_world_files = AdlsToGoogleCloudStorageOperator(</span>
<span class="sd"> task_id=&#39;copy_world_files&#39;,</span>
<span class="sd"> src_adls=&#39;hello/world/*.parquet&#39;,</span>
<span class="sd"> dest_gcs=&#39;gs://mybucket&#39;,</span>
<span class="sd"> replace=False,</span>
<span class="sd"> azure_data_lake_conn_id=&#39;azure_data_lake_default&#39;,</span>
<span class="sd"> google_cloud_storage_conn_id=&#39;google_cloud_default&#39;</span>
<span class="sd"> )</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="AdlsToGoogleCloudStorageOperator.template_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/adls_to_gcs/index.html#airflow.contrib.operators.adls_to_gcs.AdlsToGoogleCloudStorageOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;src_adls&#39;</span><span class="p">,</span> <span class="s1">&#39;dest_gcs&#39;</span><span class="p">)</span></div>
<div class="viewcode-block" id="AdlsToGoogleCloudStorageOperator.ui_color"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/adls_to_gcs/index.html#airflow.contrib.operators.adls_to_gcs.AdlsToGoogleCloudStorageOperator.ui_color">[docs]</a> <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">&#39;#f0eee4&#39;</span></div>
<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">src_adls</span><span class="p">,</span>
<span class="n">dest_gcs</span><span class="p">,</span>
<span class="n">azure_data_lake_conn_id</span><span class="p">,</span>
<span class="n">google_cloud_storage_conn_id</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">replace</span><span class="o">=</span><span class="kc">False</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">AdlsToGoogleCloudStorageOperator</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="n">path</span><span class="o">=</span><span class="n">src_adls</span><span class="p">,</span>
<span class="n">azure_data_lake_conn_id</span><span class="o">=</span><span class="n">azure_data_lake_conn_id</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">src_adls</span> <span class="o">=</span> <span class="n">src_adls</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dest_gcs</span> <span class="o">=</span> <span class="n">dest_gcs</span>
<span class="bp">self</span><span class="o">.</span><span class="n">replace</span> <span class="o">=</span> <span class="n">replace</span>
<span class="bp">self</span><span class="o">.</span><span class="n">google_cloud_storage_conn_id</span> <span class="o">=</span> <span class="n">google_cloud_storage_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>
<div class="viewcode-block" id="AdlsToGoogleCloudStorageOperator.execute"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/adls_to_gcs/index.html#airflow.contrib.operators.adls_to_gcs.AdlsToGoogleCloudStorageOperator.execute">[docs]</a> <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="c1"># use the super to list all files in an Azure Data Lake path</span>
<span class="n">files</span> <span class="o">=</span> <span class="nb">super</span><span class="p">(</span><span class="n">AdlsToGoogleCloudStorageOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">context</span><span class="p">)</span>
<span class="n">g_hook</span> <span class="o">=</span> <span class="n">GoogleCloudStorageHook</span><span class="p">(</span>
<span class="n">google_cloud_storage_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">google_cloud_storage_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="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">replace</span><span class="p">:</span>
<span class="c1"># if we are not replacing -&gt; list all files in the ADLS path</span>
<span class="c1"># and only keep those files which are present in</span>
<span class="c1"># ADLS and not in Google Cloud Storage</span>
<span class="n">bucket_name</span><span class="p">,</span> <span class="n">prefix</span> <span class="o">=</span> <span class="n">_parse_gcs_url</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">dest_gcs</span><span class="p">)</span>
<span class="n">existing_files</span> <span class="o">=</span> <span class="n">g_hook</span><span class="o">.</span><span class="n">list</span><span class="p">(</span><span class="n">bucket</span><span class="o">=</span><span class="n">bucket_name</span><span class="p">,</span> <span class="n">prefix</span><span class="o">=</span><span class="n">prefix</span><span class="p">)</span>
<span class="n">files</span> <span class="o">=</span> <span class="nb">set</span><span class="p">(</span><span class="n">files</span><span class="p">)</span> <span class="o">-</span> <span class="nb">set</span><span class="p">(</span><span class="n">existing_files</span><span class="p">)</span>
<span class="k">if</span> <span class="n">files</span><span class="p">:</span>
<span class="n">hook</span> <span class="o">=</span> <span class="n">AzureDataLakeHook</span><span class="p">(</span>
<span class="n">azure_data_lake_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">azure_data_lake_conn_id</span>
<span class="p">)</span>
<span class="k">for</span> <span class="n">obj</span> <span class="ow">in</span> <span class="n">files</span><span class="p">:</span>
<span class="k">with</span> <span class="n">NamedTemporaryFile</span><span class="p">(</span><span class="n">mode</span><span class="o">=</span><span class="s1">&#39;wb&#39;</span><span class="p">,</span> <span class="n">delete</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
<span class="n">hook</span><span class="o">.</span><span class="n">download_file</span><span class="p">(</span><span class="n">local_path</span><span class="o">=</span><span class="n">f</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="n">remote_path</span><span class="o">=</span><span class="n">obj</span><span class="p">)</span>
<span class="n">f</span><span class="o">.</span><span class="n">flush</span><span class="p">()</span>
<span class="n">dest_gcs_bucket</span><span class="p">,</span> <span class="n">dest_gcs_prefix</span> <span class="o">=</span> <span class="n">_parse_gcs_url</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">dest_gcs</span><span class="p">)</span>
<span class="n">dest_path</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">dest_gcs_prefix</span><span class="p">,</span> <span class="n">obj</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;Saving file to </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">dest_path</span><span class="p">)</span>
<span class="n">g_hook</span><span class="o">.</span><span class="n">upload</span><span class="p">(</span><span class="n">bucket</span><span class="o">=</span><span class="n">dest_gcs_bucket</span><span class="p">,</span> <span class="nb">object</span><span class="o">=</span><span class="n">dest_path</span><span class="p">,</span> <span class="n">filename</span><span class="o">=</span><span class="n">f</span><span class="o">.</span><span class="n">name</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;All done, uploaded </span><span class="si">%d</span><span class="s2"> files to GCS&quot;</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">files</span><span class="p">))</span>
<span class="k">else</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;In sync, no files needed to be uploaded to GCS&quot;</span><span class="p">)</span>
<span class="k">return</span> <span class="n">files</span></div></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">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>