blob: 7cb1d4aae2c7f40333a942d58fea67b01978796a [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.operators.s3_file_transform_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 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="../../../lineage.html">Lineage</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.operators.s3_file_transform_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.operators.s3_file_transform_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">tempfile</span> <span class="k">import</span> <span class="n">NamedTemporaryFile</span>
<span class="kn">import</span> <span class="nn">subprocess</span>
<span class="kn">import</span> <span class="nn">sys</span>
<span class="kn">from</span> <span class="nn">airflow.exceptions</span> <span class="k">import</span> <span class="n">AirflowException</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.models</span> <span class="k">import</span> <span class="n">BaseOperator</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="S3FileTransformOperator"><a class="viewcode-back" href="../../../integration.html#airflow.operators.s3_file_transform_operator.S3FileTransformOperator">[docs]</a><span class="k">class</span> <span class="nc">S3FileTransformOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Copies data from a source S3 location to a temporary location on the</span>
<span class="sd"> local filesystem. Runs a transformation on this file as specified by</span>
<span class="sd"> the transformation script and uploads the output to a destination S3</span>
<span class="sd"> location.</span>
<span class="sd"> The locations of the source and the destination files in the local</span>
<span class="sd"> filesystem is provided as an first and second arguments to the</span>
<span class="sd"> transformation script. The transformation script is expected to read the</span>
<span class="sd"> data from source, transform it and write the output to the local</span>
<span class="sd"> destination file. The operator then takes over control and uploads the</span>
<span class="sd"> local destination file to S3.</span>
<span class="sd"> S3 Select is also available to filter the source contents. Users can</span>
<span class="sd"> omit the transformation script if S3 Select expression is specified.</span>
<span class="sd"> :param source_s3_key: The key to be retrieved from S3. (templated)</span>
<span class="sd"> :type source_s3_key: str</span>
<span class="sd"> :param source_aws_conn_id: source s3 connection</span>
<span class="sd"> :type source_aws_conn_id: str</span>
<span class="sd"> :param dest_s3_key: The key to be written from S3. (templated)</span>
<span class="sd"> :type dest_s3_key: str</span>
<span class="sd"> :param dest_aws_conn_id: destination s3 connection</span>
<span class="sd"> :type dest_aws_conn_id: str</span>
<span class="sd"> :param replace: Replace dest S3 key if it already exists</span>
<span class="sd"> :type replace: bool</span>
<span class="sd"> :param transform_script: location of the executable transformation script</span>
<span class="sd"> :type transform_script: str</span>
<span class="sd"> :param select_expression: S3 Select expression</span>
<span class="sd"> :type select_expression: str</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;source_s3_key&#39;</span><span class="p">,</span> <span class="s1">&#39;dest_s3_key&#39;</span><span class="p">)</span>
<span class="n">template_ext</span> <span class="o">=</span> <span class="p">()</span>
<span class="n">ui_color</span> <span class="o">=</span> <span class="s1">&#39;#f9c915&#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">source_s3_key</span><span class="p">,</span>
<span class="n">dest_s3_key</span><span class="p">,</span>
<span class="n">transform_script</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">select_expression</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">source_aws_conn_id</span><span class="o">=</span><span class="s1">&#39;aws_default&#39;</span><span class="p">,</span>
<span class="n">dest_aws_conn_id</span><span class="o">=</span><span class="s1">&#39;aws_default&#39;</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">S3FileTransformOperator</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">source_s3_key</span> <span class="o">=</span> <span class="n">source_s3_key</span>
<span class="bp">self</span><span class="o">.</span><span class="n">source_aws_conn_id</span> <span class="o">=</span> <span class="n">source_aws_conn_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dest_s3_key</span> <span class="o">=</span> <span class="n">dest_s3_key</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dest_aws_conn_id</span> <span class="o">=</span> <span class="n">dest_aws_conn_id</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">transform_script</span> <span class="o">=</span> <span class="n">transform_script</span>
<span class="bp">self</span><span class="o">.</span><span class="n">select_expression</span> <span class="o">=</span> <span class="n">select_expression</span>
<span class="bp">self</span><span class="o">.</span><span class="n">output_encoding</span> <span class="o">=</span> <span class="n">sys</span><span class="o">.</span><span class="n">getdefaultencoding</span><span class="p">()</span>
<div class="viewcode-block" id="S3FileTransformOperator.execute"><a class="viewcode-back" href="../../../integration.html#airflow.operators.s3_file_transform_operator.S3FileTransformOperator.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="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">transform_script</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">select_expression</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span>
<span class="s2">&quot;Either transform_script or select_expression must be specified&quot;</span><span class="p">)</span>
<span class="n">source_s3</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">source_aws_conn_id</span><span class="p">)</span>
<span class="n">dest_s3</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">dest_aws_conn_id</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;Downloading source S3 file </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">source_s3_key</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">source_s3</span><span class="o">.</span><span class="n">check_for_key</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">source_s3_key</span><span class="p">):</span>
<span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span>
<span class="s2">&quot;The source key </span><span class="si">{0}</span><span class="s2"> does not exist&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">source_s3_key</span><span class="p">))</span>
<span class="n">source_s3_key_object</span> <span class="o">=</span> <span class="n">source_s3</span><span class="o">.</span><span class="n">get_key</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">source_s3_key</span><span class="p">)</span>
<span class="k">with</span> <span class="n">NamedTemporaryFile</span><span class="p">(</span><span class="s2">&quot;wb&quot;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f_source</span><span class="p">,</span> <span class="n">NamedTemporaryFile</span><span class="p">(</span><span class="s2">&quot;wb&quot;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f_dest</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;Dumping S3 file </span><span class="si">%s</span><span class="s2"> contents to local file </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">source_s3_key</span><span class="p">,</span> <span class="n">f_source</span><span class="o">.</span><span class="n">name</span>
<span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">select_expression</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">content</span> <span class="o">=</span> <span class="n">source_s3</span><span class="o">.</span><span class="n">select_key</span><span class="p">(</span>
<span class="n">key</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">source_s3_key</span><span class="p">,</span>
<span class="n">expression</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">select_expression</span>
<span class="p">)</span>
<span class="n">f_source</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="n">content</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="s2">&quot;utf-8&quot;</span><span class="p">))</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">source_s3_key_object</span><span class="o">.</span><span class="n">download_fileobj</span><span class="p">(</span><span class="n">Fileobj</span><span class="o">=</span><span class="n">f_source</span><span class="p">)</span>
<span class="n">f_source</span><span class="o">.</span><span class="n">flush</span><span class="p">()</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">transform_script</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">process</span> <span class="o">=</span> <span class="n">subprocess</span><span class="o">.</span><span class="n">Popen</span><span class="p">(</span>
<span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">transform_script</span><span class="p">,</span> <span class="n">f_source</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="n">f_dest</span><span class="o">.</span><span class="n">name</span><span class="p">],</span>
<span class="n">stdout</span><span class="o">=</span><span class="n">subprocess</span><span class="o">.</span><span class="n">PIPE</span><span class="p">,</span>
<span class="n">stderr</span><span class="o">=</span><span class="n">subprocess</span><span class="o">.</span><span class="n">STDOUT</span><span class="p">,</span>
<span class="n">close_fds</span><span class="o">=</span><span class="kc">True</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;Output:&quot;</span><span class="p">)</span>
<span class="k">for</span> <span class="n">line</span> <span class="ow">in</span> <span class="nb">iter</span><span class="p">(</span><span class="n">process</span><span class="o">.</span><span class="n">stdout</span><span class="o">.</span><span class="n">readline</span><span class="p">,</span> <span class="sa">b</span><span class="s1">&#39;&#39;</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="n">line</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">output_encoding</span><span class="p">)</span><span class="o">.</span><span class="n">rstrip</span><span class="p">())</span>
<span class="n">process</span><span class="o">.</span><span class="n">wait</span><span class="p">()</span>
<span class="k">if</span> <span class="n">process</span><span class="o">.</span><span class="n">returncode</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">:</span>
<span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span>
<span class="s2">&quot;Transform script failed: </span><span class="si">{0}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">process</span><span class="o">.</span><span class="n">returncode</span><span class="p">)</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;Transform script successful. Output temporarily located at </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span>
<span class="n">f_dest</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;Uploading transformed file to S3&quot;</span><span class="p">)</span>
<span class="n">f_dest</span><span class="o">.</span><span class="n">flush</span><span class="p">()</span>
<span class="n">dest_s3</span><span class="o">.</span><span class="n">load_file</span><span class="p">(</span>
<span class="n">filename</span><span class="o">=</span><span class="n">f_dest</span><span class="o">.</span><span class="n">name</span><span class="p">,</span>
<span class="n">key</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">dest_s3_key</span><span class="p">,</span>
<span class="n">replace</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">replace</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;Upload successful&quot;</span><span class="p">)</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" 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/js/theme.js"></script>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>