blob: ef9b718e7067da37e7d910073c50eb71da85c867 [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.aws_athena_operator &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.aws_athena_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.aws_athena_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="c1">#</span>
<span class="kn">from</span> <span class="nn">uuid</span> <span class="k">import</span> <span class="n">uuid4</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>
<span class="kn">from</span> <span class="nn">airflow.contrib.hooks.aws_athena_hook</span> <span class="k">import</span> <span class="n">AWSAthenaHook</span>
<div class="viewcode-block" id="AWSAthenaOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/aws_athena_operator/index.html#airflow.contrib.operators.aws_athena_operator.AWSAthenaOperator">[docs]</a><span class="k">class</span> <span class="nc">AWSAthenaOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> An operator that submit presto query to athena.</span>
<span class="sd"> If ``do_xcom_push`` is True, the QueryExecutionID assigned to the</span>
<span class="sd"> query will be pushed to an XCom when it successfuly completes.</span>
<span class="sd"> :param query: Presto to be run on athena. (templated)</span>
<span class="sd"> :type query: str</span>
<span class="sd"> :param database: Database to select. (templated)</span>
<span class="sd"> :type database: str</span>
<span class="sd"> :param output_location: s3 path to write the query results into. (templated)</span>
<span class="sd"> :type output_location: str</span>
<span class="sd"> :param aws_conn_id: aws connection to use</span>
<span class="sd"> :type aws_conn_id: str</span>
<span class="sd"> :param sleep_time: Time to wait between two consecutive call to check query status on athena</span>
<span class="sd"> :type sleep_time: int</span>
<span class="sd"> :param max_tries: Number of times to poll for query state before function exits</span>
<span class="sd"> :type max_triex: int</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="AWSAthenaOperator.ui_color"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/aws_athena_operator/index.html#airflow.contrib.operators.aws_athena_operator.AWSAthenaOperator.ui_color">[docs]</a> <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">&#39;#44b5e2&#39;</span></div>
<div class="viewcode-block" id="AWSAthenaOperator.template_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/aws_athena_operator/index.html#airflow.contrib.operators.aws_athena_operator.AWSAthenaOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;query&#39;</span><span class="p">,</span> <span class="s1">&#39;database&#39;</span><span class="p">,</span> <span class="s1">&#39;output_location&#39;</span><span class="p">)</span></div>
<div class="viewcode-block" id="AWSAthenaOperator.template_ext"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/aws_athena_operator/index.html#airflow.contrib.operators.aws_athena_operator.AWSAthenaOperator.template_ext">[docs]</a> <span class="n">template_ext</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;.sql&#39;</span><span class="p">,</span> <span class="p">)</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">query</span><span class="p">,</span> <span class="n">database</span><span class="p">,</span> <span class="n">output_location</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">client_request_token</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">query_execution_context</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">result_configuration</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">sleep_time</span><span class="o">=</span><span class="mi">30</span><span class="p">,</span> <span class="n">max_tries</span><span class="o">=</span><span class="kc">None</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">AWSAthenaOperator</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">query</span> <span class="o">=</span> <span class="n">query</span>
<span class="bp">self</span><span class="o">.</span><span class="n">database</span> <span class="o">=</span> <span class="n">database</span>
<span class="bp">self</span><span class="o">.</span><span class="n">output_location</span> <span class="o">=</span> <span class="n">output_location</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">client_request_token</span> <span class="o">=</span> <span class="n">client_request_token</span> <span class="ow">or</span> <span class="nb">str</span><span class="p">(</span><span class="n">uuid4</span><span class="p">())</span>
<span class="bp">self</span><span class="o">.</span><span class="n">query_execution_context</span> <span class="o">=</span> <span class="n">query_execution_context</span> <span class="ow">or</span> <span class="p">{}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">result_configuration</span> <span class="o">=</span> <span class="n">result_configuration</span> <span class="ow">or</span> <span class="p">{}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">sleep_time</span> <span class="o">=</span> <span class="n">sleep_time</span>
<span class="bp">self</span><span class="o">.</span><span class="n">max_tries</span> <span class="o">=</span> <span class="n">max_tries</span>
<span class="bp">self</span><span class="o">.</span><span class="n">query_execution_id</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hook</span> <span class="o">=</span> <span class="kc">None</span>
<div class="viewcode-block" id="AWSAthenaOperator.get_hook"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/aws_athena_operator/index.html#airflow.contrib.operators.aws_athena_operator.AWSAthenaOperator.get_hook">[docs]</a> <span class="k">def</span> <span class="nf">get_hook</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="n">AWSAthenaHook</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">aws_conn_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">sleep_time</span><span class="p">)</span></div>
<div class="viewcode-block" id="AWSAthenaOperator.execute"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/aws_athena_operator/index.html#airflow.contrib.operators.aws_athena_operator.AWSAthenaOperator.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="sd">&quot;&quot;&quot;</span>
<span class="sd"> Run Presto Query on Athena</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hook</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_hook</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">query_execution_context</span><span class="p">[</span><span class="s1">&#39;Database&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">database</span>
<span class="bp">self</span><span class="o">.</span><span class="n">result_configuration</span><span class="p">[</span><span class="s1">&#39;OutputLocation&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">output_location</span>
<span class="bp">self</span><span class="o">.</span><span class="n">query_execution_id</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">hook</span><span class="o">.</span><span class="n">run_query</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">query</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">query_execution_context</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">result_configuration</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">client_request_token</span><span class="p">)</span>
<span class="n">query_status</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">hook</span><span class="o">.</span><span class="n">poll_query_status</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">query_execution_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_tries</span><span class="p">)</span>
<span class="k">if</span> <span class="n">query_status</span> <span class="ow">in</span> <span class="n">AWSAthenaHook</span><span class="o">.</span><span class="n">FAILURE_STATES</span><span class="p">:</span>
<span class="n">error_message</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">hook</span><span class="o">.</span><span class="n">get_state_change_reason</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">query_execution_id</span><span class="p">)</span>
<span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span>
<span class="s1">&#39;Final state of Athena job is </span><span class="si">{}</span><span class="s1">, query_execution_id is </span><span class="si">{}</span><span class="s1">. Error: </span><span class="si">{}</span><span class="s1">&#39;</span>
<span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">query_status</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">query_execution_id</span><span class="p">,</span> <span class="n">error_message</span><span class="p">))</span>
<span class="k">elif</span> <span class="ow">not</span> <span class="n">query_status</span> <span class="ow">or</span> <span class="n">query_status</span> <span class="ow">in</span> <span class="n">AWSAthenaHook</span><span class="o">.</span><span class="n">INTERMEDIATE_STATES</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span>
<span class="s1">&#39;Final state of Athena job is </span><span class="si">{}</span><span class="s1">. &#39;</span>
<span class="s1">&#39;Max tries of poll status exceeded, query_execution_id is </span><span class="si">{}</span><span class="s1">.&#39;</span>
<span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">query_status</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">query_execution_id</span><span class="p">))</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">query_execution_id</span></div>
<div class="viewcode-block" id="AWSAthenaOperator.on_kill"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/aws_athena_operator/index.html#airflow.contrib.operators.aws_athena_operator.AWSAthenaOperator.on_kill">[docs]</a> <span class="k">def</span> <span class="nf">on_kill</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Cancel the submitted athena query</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">query_execution_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="s1">&#39;⚰️⚰️⚰️ Received a kill Signal. Time to Die&#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="s1">&#39;Stopping Query with executionId - </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">query_execution_id</span>
<span class="p">)</span>
<span class="n">response</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">hook</span><span class="o">.</span><span class="n">stop_query</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">query_execution_id</span><span class="p">)</span>
<span class="n">http_status_code</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">http_status_code</span> <span class="o">=</span> <span class="n">response</span><span class="p">[</span><span class="s1">&#39;ResponseMetadata&#39;</span><span class="p">][</span><span class="s1">&#39;HTTPStatusCode&#39;</span><span class="p">]</span>
<span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">ex</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">error</span><span class="p">(</span><span class="s1">&#39;Exception while cancelling query&#39;</span><span class="p">,</span> <span class="n">ex</span><span class="p">)</span>
<span class="k">finally</span><span class="p">:</span>
<span class="k">if</span> <span class="n">http_status_code</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">http_status_code</span> <span class="o">!=</span> <span class="mi">200</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">error</span><span class="p">(</span><span class="s1">&#39;Unable to request query cancel on athena. Exiting&#39;</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="s1">&#39;Polling Athena for query with id </span><span class="si">%s</span><span class="s1"> to reach final state&#39;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">query_execution_id</span>
<span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hook</span><span class="o">.</span><span class="n">poll_query_status</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">query_execution_id</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">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>