| |
| |
| <!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.druid_check_operator — 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 & 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> »</li> |
| |
| <li><a href="../../index.html">Module code</a> »</li> |
| |
| <li>airflow.operators.druid_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.druid_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"># "License"); 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"># "AS IS" 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">airflow.exceptions</span> <span class="k">import</span> <span class="n">AirflowException</span> |
| <span class="kn">from</span> <span class="nn">airflow.hooks.druid_hook</span> <span class="k">import</span> <span class="n">DruidDbApiHook</span> |
| <span class="kn">from</span> <span class="nn">airflow.operators.check_operator</span> <span class="k">import</span> <span class="n">CheckOperator</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="DruidCheckOperator"><a class="viewcode-back" href="../../../code.html#airflow.operators.druid_check_operator.DruidCheckOperator">[docs]</a><span class="k">class</span> <span class="nc">DruidCheckOperator</span><span class="p">(</span><span class="n">CheckOperator</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Performs checks against Druid. The ``DruidCheckOperator`` 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 (``""``)</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's partition is</span> |
| <span class="sd"> greater than yesterday'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 alterts</span> |
| <span class="sd"> without stopping the progress of the DAG.</span> |
| |
| <span class="sd"> :param sql: the sql to be executed</span> |
| <span class="sd"> :type sql: string</span> |
| <span class="sd"> :param druid_broker_conn_id: reference to the druid broker</span> |
| <span class="sd"> :type druid_broker_conn_id: string</span> |
| <span class="sd"> """</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">druid_broker_conn_id</span><span class="o">=</span><span class="s1">'druid_broker_default'</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">DruidCheckOperator</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">sql</span><span class="o">=</span><span class="n">sql</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">druid_broker_conn_id</span> <span class="o">=</span> <span class="n">druid_broker_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="DruidCheckOperator.get_db_hook"><a class="viewcode-back" href="../../../code.html#airflow.operators.druid_check_operator.DruidCheckOperator.get_db_hook">[docs]</a> <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="sd">"""</span> |
| <span class="sd"> Return the druid db api hook.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">DruidDbApiHook</span><span class="p">(</span><span class="n">druid_broker_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">druid_broker_conn_id</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="DruidCheckOperator.get_first"><a class="viewcode-back" href="../../../code.html#airflow.operators.druid_check_operator.DruidCheckOperator.get_first">[docs]</a> <span class="k">def</span> <span class="nf">get_first</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="sd">"""</span> |
| <span class="sd"> Executes the druid sql to druid broker and returns the first resulting row.</span> |
| |
| <span class="sd"> :param sql: the sql statement to be executed (str)</span> |
| <span class="sd"> :type sql: str</span> |
| <span class="sd"> """</span> |
| <span class="k">with</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_conn</span><span class="p">()</span> <span class="k">as</span> <span class="n">cur</span><span class="p">:</span> |
| <span class="n">cur</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">sql</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">cur</span><span class="o">.</span><span class="n">fetchone</span><span class="p">()</span></div> |
| |
| <div class="viewcode-block" id="DruidCheckOperator.execute"><a class="viewcode-back" href="../../../code.html#airflow.operators.druid_check_operator.DruidCheckOperator.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">'Executing SQL check: </span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">sql</span><span class="p">))</span> |
| <span class="n">record</span> <span class="o">=</span> <span class="bp">self</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="s2">"Record: </span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">record</span><span class="p">)))</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">record</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s2">"The query returned 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="s2">"Success."</span><span class="p">)</span></div></div> |
| </pre></div> |
| |
| </div> |
| |
| </div> |
| <footer> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| |
| </p> |
| </div> |
| Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| |
| |
| |
| |
| <script type="text/javascript" id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script> |
| <script type="text/javascript" src="../../../_static/jquery.js"></script> |
| <script type="text/javascript" src="../../../_static/underscore.js"></script> |
| <script type="text/javascript" src="../../../_static/doctools.js"></script> |
| |
| |
| |
| |
| <script type="text/javascript" src="../../../_static/js/theme.js"></script> |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| </body> |
| </html> |