blob: a310379258c528f2315ccc137c25bced2247ab20 [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.hooks.aws_athena_hook &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.hooks.aws_athena_hook</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.hooks.aws_athena_hook</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">time</span> <span class="k">import</span> <span class="n">sleep</span>
<span class="kn">from</span> <span class="nn">airflow.contrib.hooks.aws_hook</span> <span class="k">import</span> <span class="n">AwsHook</span>
<div class="viewcode-block" id="AWSAthenaHook"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.hooks.aws_athena_hook.AWSAthenaHook">[docs]</a><span class="k">class</span> <span class="nc">AWSAthenaHook</span><span class="p">(</span><span class="n">AwsHook</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Interact with AWS Athena to run, poll queries and return query results</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"> &quot;&quot;&quot;</span>
<span class="n">INTERMEDIATE_STATES</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;QUEUED&#39;</span><span class="p">,</span> <span class="s1">&#39;RUNNING&#39;</span><span class="p">,)</span>
<span class="n">FAILURE_STATES</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;FAILED&#39;</span><span class="p">,</span> <span class="s1">&#39;CANCELLED&#39;</span><span class="p">,)</span>
<span class="n">SUCCESS_STATES</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;SUCCEEDED&#39;</span><span class="p">,)</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">aws_conn_id</span><span class="o">=</span><span class="s1">&#39;aws_default&#39;</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="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">AWSAthenaHook</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">aws_conn_id</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">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">conn</span> <span class="o">=</span> <span class="kc">None</span>
<div class="viewcode-block" id="AWSAthenaHook.get_conn"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.hooks.aws_athena_hook.AWSAthenaHook.get_conn">[docs]</a> <span class="k">def</span> <span class="nf">get_conn</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> check if aws conn exists already or create one and return it</span>
<span class="sd"> :return: boto3 session</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">conn</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">conn</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_client_type</span><span class="p">(</span><span class="s1">&#39;athena&#39;</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">conn</span></div>
<div class="viewcode-block" id="AWSAthenaHook.run_query"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.hooks.aws_athena_hook.AWSAthenaHook.run_query">[docs]</a> <span class="k">def</span> <span class="nf">run_query</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">query_context</span><span class="p">,</span> <span class="n">result_configuration</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="sd">&quot;&quot;&quot;</span>
<span class="sd"> Run Presto query on athena with provided config and return submitted query_execution_id</span>
<span class="sd"> :param query: Presto query to run</span>
<span class="sd"> :type query: str</span>
<span class="sd"> :param query_context: Context in which query need to be run</span>
<span class="sd"> :type query_context: dict</span>
<span class="sd"> :param result_configuration: Dict with path to store results in and config related to encryption</span>
<span class="sd"> :type result_configuration: dict</span>
<span class="sd"> :param client_request_token: Unique token created by user to avoid multiple executions of same query</span>
<span class="sd"> :type client_request_token: str</span>
<span class="sd"> :return: str</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">response</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">conn</span><span class="o">.</span><span class="n">start_query_execution</span><span class="p">(</span><span class="n">QueryString</span><span class="o">=</span><span class="n">query</span><span class="p">,</span>
<span class="n">ClientRequestToken</span><span class="o">=</span><span class="n">client_request_token</span><span class="p">,</span>
<span class="n">QueryExecutionContext</span><span class="o">=</span><span class="n">query_context</span><span class="p">,</span>
<span class="n">ResultConfiguration</span><span class="o">=</span><span class="n">result_configuration</span><span class="p">)</span>
<span class="n">query_execution_id</span> <span class="o">=</span> <span class="n">response</span><span class="p">[</span><span class="s1">&#39;QueryExecutionId&#39;</span><span class="p">]</span>
<span class="k">return</span> <span class="n">query_execution_id</span></div>
<div class="viewcode-block" id="AWSAthenaHook.check_query_status"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.hooks.aws_athena_hook.AWSAthenaHook.check_query_status">[docs]</a> <span class="k">def</span> <span class="nf">check_query_status</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query_execution_id</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Fetch the status of submitted athena query. Returns None or one of valid query states.</span>
<span class="sd"> :param query_execution_id: Id of submitted athena query</span>
<span class="sd"> :type query_execution_id: str</span>
<span class="sd"> :return: str</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">response</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">conn</span><span class="o">.</span><span class="n">get_query_execution</span><span class="p">(</span><span class="n">QueryExecutionId</span><span class="o">=</span><span class="n">query_execution_id</span><span class="p">)</span>
<span class="n">state</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">state</span> <span class="o">=</span> <span class="n">response</span><span class="p">[</span><span class="s1">&#39;QueryExecution&#39;</span><span class="p">][</span><span class="s1">&#39;Status&#39;</span><span class="p">][</span><span class="s1">&#39;State&#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 getting query state&#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">return</span> <span class="n">state</span></div>
<div class="viewcode-block" id="AWSAthenaHook.get_query_results"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.hooks.aws_athena_hook.AWSAthenaHook.get_query_results">[docs]</a> <span class="k">def</span> <span class="nf">get_query_results</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query_execution_id</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Fetch submitted athena query results. returns none if query is in intermediate state or</span>
<span class="sd"> failed/cancelled state else dict of query output</span>
<span class="sd"> :param query_execution_id: Id of submitted athena query</span>
<span class="sd"> :type query_execution_id: str</span>
<span class="sd"> :return: dict</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">query_state</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">check_query_status</span><span class="p">(</span><span class="n">query_execution_id</span><span class="p">)</span>
<span class="k">if</span> <span class="n">query_state</span> <span class="ow">is</span> <span class="kc">None</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;Invalid Query state&#39;</span><span class="p">)</span>
<span class="k">return</span> <span class="kc">None</span>
<span class="k">elif</span> <span class="n">query_state</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">INTERMEDIATE_STATES</span> <span class="ow">or</span> <span class="n">query_state</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">FAILURE_STATES</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;Query is in </span><span class="si">{state}</span><span class="s1"> state. Cannot fetch results&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">state</span><span class="o">=</span><span class="n">query_state</span><span class="p">))</span>
<span class="k">return</span> <span class="kc">None</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">conn</span><span class="o">.</span><span class="n">get_query_results</span><span class="p">(</span><span class="n">QueryExecutionId</span><span class="o">=</span><span class="n">query_execution_id</span><span class="p">)</span></div>
<div class="viewcode-block" id="AWSAthenaHook.poll_query_status"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.hooks.aws_athena_hook.AWSAthenaHook.poll_query_status">[docs]</a> <span class="k">def</span> <span class="nf">poll_query_status</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query_execution_id</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="sd">&quot;&quot;&quot;</span>
<span class="sd"> Poll the status of submitted athena query until query state reaches final state.</span>
<span class="sd"> Returns one of the final states</span>
<span class="sd"> :param query_execution_id: Id of submitted athena query</span>
<span class="sd"> :type query_execution_id: str</span>
<span class="sd"> :param max_tries: Number of times to poll for query state before function exits</span>
<span class="sd"> :type max_tries: int</span>
<span class="sd"> :return: str</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">try_number</span> <span class="o">=</span> <span class="mi">1</span>
<span class="n">final_query_state</span> <span class="o">=</span> <span class="kc">None</span> <span class="c1"># Query state when query reaches final state or max_tries reached</span>
<span class="k">while</span> <span class="kc">True</span><span class="p">:</span>
<span class="n">query_state</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">check_query_status</span><span class="p">(</span><span class="n">query_execution_id</span><span class="p">)</span>
<span class="k">if</span> <span class="n">query_state</span> <span class="ow">is</span> <span class="kc">None</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;Trial </span><span class="si">{try_number}</span><span class="s1">: Invalid query state. Retrying again&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="n">try_number</span><span class="o">=</span><span class="n">try_number</span><span class="p">))</span>
<span class="k">elif</span> <span class="n">query_state</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">INTERMEDIATE_STATES</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;Trial </span><span class="si">{try_number}</span><span class="s1">: Query is still in an intermediate state - </span><span class="si">{state}</span><span class="s1">&#39;</span>
<span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">try_number</span><span class="o">=</span><span class="n">try_number</span><span class="p">,</span> <span class="n">state</span><span class="o">=</span><span class="n">query_state</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;Trial </span><span class="si">{try_number}</span><span class="s1">: Query execution completed. Final state is </span><span class="si">{state}</span><span class="s1">&#39;</span>
<span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">try_number</span><span class="o">=</span><span class="n">try_number</span><span class="p">,</span> <span class="n">state</span><span class="o">=</span><span class="n">query_state</span><span class="p">))</span>
<span class="n">final_query_state</span> <span class="o">=</span> <span class="n">query_state</span>
<span class="k">break</span>
<span class="k">if</span> <span class="n">max_tries</span> <span class="ow">and</span> <span class="n">try_number</span> <span class="o">&gt;=</span> <span class="n">max_tries</span><span class="p">:</span> <span class="c1"># Break loop if max_tries reached</span>
<span class="n">final_query_state</span> <span class="o">=</span> <span class="n">query_state</span>
<span class="k">break</span>
<span class="n">try_number</span> <span class="o">+=</span> <span class="mi">1</span>
<span class="n">sleep</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">sleep_time</span><span class="p">)</span>
<span class="k">return</span> <span class="n">final_query_state</span></div>
<div class="viewcode-block" id="AWSAthenaHook.stop_query"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.hooks.aws_athena_hook.AWSAthenaHook.stop_query">[docs]</a> <span class="k">def</span> <span class="nf">stop_query</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query_execution_id</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Cancel the submitted athena query</span>
<span class="sd"> :param query_execution_id: Id of submitted athena query</span>
<span class="sd"> :type query_execution_id: str</span>
<span class="sd"> :return: dict</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">conn</span><span class="o">.</span><span class="n">stop_query_execution</span><span class="p">(</span><span class="n">QueryExecutionId</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" 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>