blob: 06703b9171e612f6cf0af346f56e19bce1d2a366 [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.check_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.check_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.check_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">builtins</span> <span class="k">import</span> <span class="nb">zip</span>
<span class="kn">from</span> <span class="nn">builtins</span> <span class="k">import</span> <span class="nb">str</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.base_hook</span> <span class="k">import</span> <span class="n">BaseHook</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="CheckOperator"><a class="viewcode-back" href="../../../code.html#airflow.operators.check_operator.CheckOperator">[docs]</a><span class="k">class</span> <span class="nc">CheckOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Performs checks against a db. The ``CheckOperator`` expects</span>
<span class="sd"> a sql query that will return a single row. Each value on that</span>
<span class="sd"> first row is evaluated using python ``bool`` casting. If any of the</span>
<span class="sd"> values return ``False`` the check is failed and errors out.</span>
<span class="sd"> Note that Python bool casting evals the following as ``False``:</span>
<span class="sd"> * ``False``</span>
<span class="sd"> * ``0``</span>
<span class="sd"> * Empty string (``&quot;&quot;``)</span>
<span class="sd"> * Empty list (``[]``)</span>
<span class="sd"> * Empty dictionary or set (``{}``)</span>
<span class="sd"> Given a query like ``SELECT COUNT(*) FROM foo``, it will fail only if</span>
<span class="sd"> the count ``== 0``. You can craft much more complex query that could,</span>
<span class="sd"> for instance, check that the table has the same number of rows as</span>
<span class="sd"> the source table upstream, or that the count of today&#39;s partition is</span>
<span class="sd"> greater than yesterday&#39;s partition, or that a set of metrics are less</span>
<span class="sd"> than 3 standard deviation for the 7 day average.</span>
<span class="sd"> This operator can be used as a data quality check in your pipeline, and</span>
<span class="sd"> depending on where you put it in your DAG, you have the choice to</span>
<span class="sd"> stop the critical path, preventing from</span>
<span class="sd"> publishing dubious data, or on the side and receive email alerts</span>
<span class="sd"> without stopping the progress of the DAG.</span>
<span class="sd"> Note that this is an abstract class and get_db_hook</span>
<span class="sd"> needs to be defined. Whereas a get_db_hook is hook that gets a</span>
<span class="sd"> single record from an external source.</span>
<span class="sd"> :param sql: the sql to be executed. (templated)</span>
<span class="sd"> :type sql: string</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;sql&#39;</span><span class="p">,)</span>
<span class="n">template_ext</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;.hql&#39;</span><span class="p">,</span> <span class="s1">&#39;.sql&#39;</span><span class="p">,)</span>
<span class="n">ui_color</span> <span class="o">=</span> <span class="s1">&#39;#fff7e6&#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">sql</span><span class="p">,</span>
<span class="n">conn_id</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">CheckOperator</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">conn_id</span> <span class="o">=</span> <span class="n">conn_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">sql</span> <span class="o">=</span> <span class="n">sql</span>
<div class="viewcode-block" id="CheckOperator.execute"><a class="viewcode-back" href="../../../code.html#airflow.operators.check_operator.CheckOperator.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="o">=</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;Executing SQL check: </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">sql</span><span class="p">)</span>
<span class="n">records</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_db_hook</span><span class="p">()</span><span class="o">.</span><span class="n">get_first</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">sql</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;Record: </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="n">records</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">records</span><span class="p">:</span>
<span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s2">&quot;The query returned None&quot;</span><span class="p">)</span>
<span class="k">elif</span> <span class="ow">not</span> <span class="nb">all</span><span class="p">([</span><span class="nb">bool</span><span class="p">(</span><span class="n">r</span><span class="p">)</span> <span class="k">for</span> <span class="n">r</span> <span class="ow">in</span> <span class="n">records</span><span class="p">]):</span>
<span class="n">exceptstr</span> <span class="o">=</span> <span class="s2">&quot;Test failed.</span><span class="se">\n</span><span class="s2">Query:</span><span class="se">\n</span><span class="si">{q}</span><span class="se">\n</span><span class="s2">Results:</span><span class="se">\n</span><span class="si">{r!s}</span><span class="s2">&quot;</span>
<span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="n">exceptstr</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">q</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">sql</span><span class="p">,</span> <span class="n">r</span><span class="o">=</span><span class="n">records</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;Success.&quot;</span><span class="p">)</span></div>
<span class="k">def</span> <span class="nf">get_db_hook</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="n">BaseHook</span><span class="o">.</span><span class="n">get_hook</span><span class="p">(</span><span class="n">conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">conn_id</span><span class="p">)</span></div>
<span class="k">def</span> <span class="nf">_convert_to_float_if_possible</span><span class="p">(</span><span class="n">s</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> A small helper function to convert a string to a numeric value</span>
<span class="sd"> if appropriate</span>
<span class="sd"> :param s: the string to be converted</span>
<span class="sd"> :type s: str</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">ret</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">s</span><span class="p">)</span>
<span class="k">except</span> <span class="p">(</span><span class="ne">ValueError</span><span class="p">,</span> <span class="ne">TypeError</span><span class="p">):</span>
<span class="n">ret</span> <span class="o">=</span> <span class="n">s</span>
<span class="k">return</span> <span class="n">ret</span>
<div class="viewcode-block" id="ValueCheckOperator"><a class="viewcode-back" href="../../../code.html#airflow.operators.check_operator.ValueCheckOperator">[docs]</a><span class="k">class</span> <span class="nc">ValueCheckOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Performs a simple value check using sql code.</span>
<span class="sd"> Note that this is an abstract class and get_db_hook</span>
<span class="sd"> needs to be defined. Whereas a get_db_hook is hook that gets a</span>
<span class="sd"> single record from an external source.</span>
<span class="sd"> :param sql: the sql to be executed. (templated)</span>
<span class="sd"> :type sql: string</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">__mapper_args__</span> <span class="o">=</span> <span class="p">{</span>
<span class="s1">&#39;polymorphic_identity&#39;</span><span class="p">:</span> <span class="s1">&#39;ValueCheckOperator&#39;</span>
<span class="p">}</span>
<span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;sql&#39;</span><span class="p">,</span> <span class="s1">&#39;pass_value&#39;</span><span class="p">,)</span>
<span class="n">template_ext</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;.hql&#39;</span><span class="p">,</span> <span class="s1">&#39;.sql&#39;</span><span class="p">,)</span>
<span class="n">ui_color</span> <span class="o">=</span> <span class="s1">&#39;#fff7e6&#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">sql</span><span class="p">,</span> <span class="n">pass_value</span><span class="p">,</span> <span class="n">tolerance</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">conn_id</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">ValueCheckOperator</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">sql</span> <span class="o">=</span> <span class="n">sql</span>
<span class="bp">self</span><span class="o">.</span><span class="n">conn_id</span> <span class="o">=</span> <span class="n">conn_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">pass_value</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">pass_value</span><span class="p">)</span>
<span class="n">tol</span> <span class="o">=</span> <span class="n">_convert_to_float_if_possible</span><span class="p">(</span><span class="n">tolerance</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">tol</span> <span class="o">=</span> <span class="n">tol</span> <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">tol</span><span class="p">,</span> <span class="nb">float</span><span class="p">)</span> <span class="k">else</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">has_tolerance</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">tol</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span>
<div class="viewcode-block" id="ValueCheckOperator.execute"><a class="viewcode-back" href="../../../code.html#airflow.operators.check_operator.ValueCheckOperator.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="o">=</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;Executing SQL check: </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">sql</span><span class="p">)</span>
<span class="n">records</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_db_hook</span><span class="p">()</span><span class="o">.</span><span class="n">get_first</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">sql</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">records</span><span class="p">:</span>
<span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s2">&quot;The query returned None&quot;</span><span class="p">)</span>
<span class="n">pass_value_conv</span> <span class="o">=</span> <span class="n">_convert_to_float_if_possible</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">pass_value</span><span class="p">)</span>
<span class="n">is_numeric_value_check</span> <span class="o">=</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">pass_value_conv</span><span class="p">,</span> <span class="nb">float</span><span class="p">)</span>
<span class="n">tolerance_pct_str</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">tol</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">):</span>
<span class="n">tolerance_pct_str</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">tol</span> <span class="o">*</span> <span class="mi">100</span><span class="p">)</span> <span class="o">+</span> <span class="s1">&#39;%&#39;</span>
<span class="n">except_temp</span> <span class="o">=</span> <span class="p">(</span><span class="s2">&quot;Test failed.</span><span class="se">\n</span><span class="s2">Pass value:</span><span class="si">{pass_value_conv}</span><span class="se">\n</span><span class="s2">&quot;</span>
<span class="s2">&quot;Tolerance:</span><span class="si">{tolerance_pct_str}</span><span class="se">\n</span><span class="s2">&quot;</span>
<span class="s2">&quot;Query:</span><span class="se">\n</span><span class="si">{self.sql}</span><span class="se">\n</span><span class="s2">Results:</span><span class="se">\n</span><span class="si">{records!s}</span><span class="s2">&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">is_numeric_value_check</span><span class="p">:</span>
<span class="n">tests</span> <span class="o">=</span> <span class="p">[</span><span class="nb">str</span><span class="p">(</span><span class="n">r</span><span class="p">)</span> <span class="o">==</span> <span class="n">pass_value_conv</span> <span class="k">for</span> <span class="n">r</span> <span class="ow">in</span> <span class="n">records</span><span class="p">]</span>
<span class="k">elif</span> <span class="n">is_numeric_value_check</span><span class="p">:</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">num_rec</span> <span class="o">=</span> <span class="p">[</span><span class="nb">float</span><span class="p">(</span><span class="n">r</span><span class="p">)</span> <span class="k">for</span> <span class="n">r</span> <span class="ow">in</span> <span class="n">records</span><span class="p">]</span>
<span class="k">except</span> <span class="p">(</span><span class="ne">ValueError</span><span class="p">,</span> <span class="ne">TypeError</span><span class="p">)</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="n">cvestr</span> <span class="o">=</span> <span class="s2">&quot;Converting a result to float failed.</span><span class="se">\n</span><span class="s2">&quot;</span>
<span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="n">cvestr</span> <span class="o">+</span> <span class="n">except_temp</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="o">**</span><span class="nb">locals</span><span class="p">()))</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">has_tolerance</span><span class="p">:</span>
<span class="n">tests</span> <span class="o">=</span> <span class="p">[</span>
<span class="n">pass_value_conv</span> <span class="o">*</span> <span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">tol</span><span class="p">)</span> <span class="o">&lt;=</span>
<span class="n">r</span> <span class="o">&lt;=</span> <span class="n">pass_value_conv</span> <span class="o">*</span> <span class="p">(</span><span class="mi">1</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">tol</span><span class="p">)</span>
<span class="k">for</span> <span class="n">r</span> <span class="ow">in</span> <span class="n">num_rec</span><span class="p">]</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">tests</span> <span class="o">=</span> <span class="p">[</span><span class="n">r</span> <span class="o">==</span> <span class="n">pass_value_conv</span> <span class="k">for</span> <span class="n">r</span> <span class="ow">in</span> <span class="n">num_rec</span><span class="p">]</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">all</span><span class="p">(</span><span class="n">tests</span><span class="p">):</span>
<span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="n">except_temp</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="o">**</span><span class="nb">locals</span><span class="p">()))</span></div>
<span class="k">def</span> <span class="nf">get_db_hook</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="n">BaseHook</span><span class="o">.</span><span class="n">get_hook</span><span class="p">(</span><span class="n">conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">conn_id</span><span class="p">)</span></div>
<div class="viewcode-block" id="IntervalCheckOperator"><a class="viewcode-back" href="../../../code.html#airflow.operators.check_operator.IntervalCheckOperator">[docs]</a><span class="k">class</span> <span class="nc">IntervalCheckOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Checks that the values of metrics given as SQL expressions are within</span>
<span class="sd"> a certain tolerance of the ones from days_back before.</span>
<span class="sd"> Note that this is an abstract class and get_db_hook</span>
<span class="sd"> needs to be defined. Whereas a get_db_hook is hook that gets a</span>
<span class="sd"> single record from an external source.</span>
<span class="sd"> :param table: the table name</span>
<span class="sd"> :type table: str</span>
<span class="sd"> :param days_back: number of days between ds and the ds we want to check</span>
<span class="sd"> against. Defaults to 7 days</span>
<span class="sd"> :type days_back: int</span>
<span class="sd"> :param metrics_threshold: a dictionary of ratios indexed by metrics</span>
<span class="sd"> :type metrics_threshold: dict</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">__mapper_args__</span> <span class="o">=</span> <span class="p">{</span>
<span class="s1">&#39;polymorphic_identity&#39;</span><span class="p">:</span> <span class="s1">&#39;IntervalCheckOperator&#39;</span>
<span class="p">}</span>
<span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;sql1&#39;</span><span class="p">,</span> <span class="s1">&#39;sql2&#39;</span><span class="p">)</span>
<span class="n">template_ext</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;.hql&#39;</span><span class="p">,</span> <span class="s1">&#39;.sql&#39;</span><span class="p">,)</span>
<span class="n">ui_color</span> <span class="o">=</span> <span class="s1">&#39;#fff7e6&#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">table</span><span class="p">,</span> <span class="n">metrics_thresholds</span><span class="p">,</span>
<span class="n">date_filter_column</span><span class="o">=</span><span class="s1">&#39;ds&#39;</span><span class="p">,</span> <span class="n">days_back</span><span class="o">=-</span><span class="mi">7</span><span class="p">,</span>
<span class="n">conn_id</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">IntervalCheckOperator</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">table</span> <span class="o">=</span> <span class="n">table</span>
<span class="bp">self</span><span class="o">.</span><span class="n">metrics_thresholds</span> <span class="o">=</span> <span class="n">metrics_thresholds</span>
<span class="bp">self</span><span class="o">.</span><span class="n">metrics_sorted</span> <span class="o">=</span> <span class="nb">sorted</span><span class="p">(</span><span class="n">metrics_thresholds</span><span class="o">.</span><span class="n">keys</span><span class="p">())</span>
<span class="bp">self</span><span class="o">.</span><span class="n">date_filter_column</span> <span class="o">=</span> <span class="n">date_filter_column</span>
<span class="bp">self</span><span class="o">.</span><span class="n">days_back</span> <span class="o">=</span> <span class="o">-</span><span class="nb">abs</span><span class="p">(</span><span class="n">days_back</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">conn_id</span> <span class="o">=</span> <span class="n">conn_id</span>
<span class="n">sqlexp</span> <span class="o">=</span> <span class="s1">&#39;, &#39;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">metrics_sorted</span><span class="p">)</span>
<span class="n">sqlt</span> <span class="o">=</span> <span class="p">(</span><span class="s2">&quot;SELECT </span><span class="si">{sqlexp}</span><span class="s2"> FROM </span><span class="si">{table}</span><span class="s2">&quot;</span>
<span class="s2">&quot; WHERE </span><span class="si">{date_filter_column}</span><span class="s2">=&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="o">**</span><span class="nb">locals</span><span class="p">())</span>
<span class="bp">self</span><span class="o">.</span><span class="n">sql1</span> <span class="o">=</span> <span class="n">sqlt</span> <span class="o">+</span> <span class="s2">&quot;&#39;{{ ds }}&#39;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">sql2</span> <span class="o">=</span> <span class="n">sqlt</span> <span class="o">+</span> <span class="s2">&quot;&#39;{{ macros.ds_add(ds, &quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">days_back</span><span class="p">)</span> <span class="o">+</span> <span class="s2">&quot;) }}&#39;&quot;</span>
<div class="viewcode-block" id="IntervalCheckOperator.execute"><a class="viewcode-back" href="../../../code.html#airflow.operators.check_operator.IntervalCheckOperator.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="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="n">hook</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_db_hook</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;Executing SQL check: </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">sql2</span><span class="p">)</span>
<span class="n">row2</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">get_first</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">sql2</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;Executing SQL check: </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">sql1</span><span class="p">)</span>
<span class="n">row1</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">get_first</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">sql1</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">row2</span><span class="p">:</span>
<span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s2">&quot;The query </span><span class="si">{q}</span><span class="s2"> returned None&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">q</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">sql2</span><span class="p">))</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">row1</span><span class="p">:</span>
<span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s2">&quot;The query </span><span class="si">{q}</span><span class="s2"> returned None&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">q</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">sql1</span><span class="p">))</span>
<span class="n">current</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span><span class="nb">zip</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">metrics_sorted</span><span class="p">,</span> <span class="n">row1</span><span class="p">))</span>
<span class="n">reference</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span><span class="nb">zip</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">metrics_sorted</span><span class="p">,</span> <span class="n">row2</span><span class="p">))</span>
<span class="n">ratios</span> <span class="o">=</span> <span class="p">{}</span>
<span class="n">test_results</span> <span class="o">=</span> <span class="p">{}</span>
<span class="n">rlog</span> <span class="o">=</span> <span class="s2">&quot;Ratio for </span><span class="si">{0}</span><span class="s2">: </span><span class="si">{1}</span><span class="s2"> </span><span class="se">\n</span><span class="s2"> Ratio threshold : </span><span class="si">{2}</span><span class="s2">&quot;</span>
<span class="n">fstr</span> <span class="o">=</span> <span class="s2">&quot;&#39;</span><span class="si">{k}</span><span class="s2">&#39; check failed. </span><span class="si">{r}</span><span class="s2"> is above </span><span class="si">{tr}</span><span class="s2">&quot;</span>
<span class="n">estr</span> <span class="o">=</span> <span class="s2">&quot;The following tests have failed:</span><span class="se">\n</span><span class="s2"> </span><span class="si">{0}</span><span class="s2">&quot;</span>
<span class="n">countstr</span> <span class="o">=</span> <span class="s2">&quot;The following </span><span class="si">{j}</span><span class="s2"> tests out of </span><span class="si">{n}</span><span class="s2"> failed:&quot;</span>
<span class="k">for</span> <span class="n">m</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">metrics_sorted</span><span class="p">:</span>
<span class="k">if</span> <span class="n">current</span><span class="p">[</span><span class="n">m</span><span class="p">]</span> <span class="o">==</span> <span class="mi">0</span> <span class="ow">or</span> <span class="n">reference</span><span class="p">[</span><span class="n">m</span><span class="p">]</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="n">ratio</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">ratio</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="nb">max</span><span class="p">(</span><span class="n">current</span><span class="p">[</span><span class="n">m</span><span class="p">],</span> <span class="n">reference</span><span class="p">[</span><span class="n">m</span><span class="p">]))</span> <span class="o">/</span> \
<span class="nb">min</span><span class="p">(</span><span class="n">current</span><span class="p">[</span><span class="n">m</span><span class="p">],</span> <span class="n">reference</span><span class="p">[</span><span class="n">m</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">rlog</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">m</span><span class="p">,</span> <span class="n">ratio</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">metrics_thresholds</span><span class="p">[</span><span class="n">m</span><span class="p">]))</span>
<span class="n">ratios</span><span class="p">[</span><span class="n">m</span><span class="p">]</span> <span class="o">=</span> <span class="n">ratio</span>
<span class="n">test_results</span><span class="p">[</span><span class="n">m</span><span class="p">]</span> <span class="o">=</span> <span class="n">ratio</span> <span class="o">&lt;</span> <span class="bp">self</span><span class="o">.</span><span class="n">metrics_thresholds</span><span class="p">[</span><span class="n">m</span><span class="p">]</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">all</span><span class="p">(</span><span class="n">test_results</span><span class="o">.</span><span class="n">values</span><span class="p">()):</span>
<span class="n">failed_tests</span> <span class="o">=</span> <span class="p">[</span><span class="n">it</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">it</span> <span class="ow">in</span> <span class="n">test_results</span><span class="o">.</span><span class="n">items</span><span class="p">()</span> <span class="k">if</span> <span class="ow">not</span> <span class="n">it</span><span class="p">[</span><span class="mi">1</span><span class="p">]]</span>
<span class="n">j</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">failed_tests</span><span class="p">)</span>
<span class="n">n</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">metrics_sorted</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">warning</span><span class="p">(</span><span class="n">countstr</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="o">**</span><span class="nb">locals</span><span class="p">()))</span>
<span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">failed_tests</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">warning</span><span class="p">(</span>
<span class="n">fstr</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">k</span><span class="o">=</span><span class="n">k</span><span class="p">,</span> <span class="n">r</span><span class="o">=</span><span class="n">ratios</span><span class="p">[</span><span class="n">k</span><span class="p">],</span> <span class="n">tr</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">metrics_thresholds</span><span class="p">[</span><span class="n">k</span><span class="p">])</span>
<span class="p">)</span>
<span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="n">estr</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="s2">&quot;, &quot;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">failed_tests</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 tests have passed&quot;</span><span class="p">)</span></div>
<span class="k">def</span> <span class="nf">get_db_hook</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="n">BaseHook</span><span class="o">.</span><span class="n">get_hook</span><span class="p">(</span><span class="n">conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">conn_id</span><span class="p">)</span></div>
</pre></div>
</div>
</div>
<footer>
<hr/>
<div role="contentinfo">
<p>
</p>
</div>
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript" id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../_static/js/theme.js"></script>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>