blob: 46f5c4a7517a05893e921992567925165d1324be [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.bigquery_check_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">
1.10.3
</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.bigquery_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.contrib.operators.bigquery_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">airflow.contrib.hooks.bigquery_hook</span> <span class="k">import</span> <span class="n">BigQueryHook</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="p">,</span> <span class="n">ValueCheckOperator</span><span class="p">,</span> <span class="n">IntervalCheckOperator</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="BigQueryCheckOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/bigquery_check_operator/index.html#airflow.contrib.operators.bigquery_check_operator.BigQueryCheckOperator">[docs]</a><span class="k">class</span> <span class="nc">BigQueryCheckOperator</span><span class="p">(</span><span class="n">CheckOperator</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Performs checks against BigQuery. The ``BigQueryCheckOperator`` 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"> :param sql: the sql to be executed</span>
<span class="sd"> :type sql: str</span>
<span class="sd"> :param bigquery_conn_id: reference to the BigQuery database</span>
<span class="sd"> :type bigquery_conn_id: str</span>
<span class="sd"> :param use_legacy_sql: Whether to use legacy SQL (true)</span>
<span class="sd"> or standard SQL (false).</span>
<span class="sd"> :type use_legacy_sql: bool</span>
<span class="sd"> &quot;&quot;&quot;</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">bigquery_conn_id</span><span class="o">=</span><span class="s1">&#39;bigquery_default&#39;</span><span class="p">,</span>
<span class="n">use_legacy_sql</span><span class="o">=</span><span class="kc">True</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">BigQueryCheckOperator</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">bigquery_conn_id</span> <span class="o">=</span> <span class="n">bigquery_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>
<span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_sql</span> <span class="o">=</span> <span class="n">use_legacy_sql</span>
<div class="viewcode-block" id="BigQueryCheckOperator.get_db_hook"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/bigquery_check_operator/index.html#airflow.contrib.operators.bigquery_check_operator.BigQueryCheckOperator.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="k">return</span> <span class="n">BigQueryHook</span><span class="p">(</span><span class="n">bigquery_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">bigquery_conn_id</span><span class="p">,</span>
<span class="n">use_legacy_sql</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_sql</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="BigQueryValueCheckOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/bigquery_check_operator/index.html#airflow.contrib.operators.bigquery_check_operator.BigQueryValueCheckOperator">[docs]</a><span class="k">class</span> <span class="nc">BigQueryValueCheckOperator</span><span class="p">(</span><span class="n">ValueCheckOperator</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"> :param sql: the sql to be executed</span>
<span class="sd"> :type sql: str</span>
<span class="sd"> :param use_legacy_sql: Whether to use legacy SQL (true)</span>
<span class="sd"> or standard SQL (false).</span>
<span class="sd"> :type use_legacy_sql: bool</span>
<span class="sd"> &quot;&quot;&quot;</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">bigquery_conn_id</span><span class="o">=</span><span class="s1">&#39;bigquery_default&#39;</span><span class="p">,</span>
<span class="n">use_legacy_sql</span><span class="o">=</span><span class="kc">True</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">BigQueryValueCheckOperator</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="n">pass_value</span><span class="o">=</span><span class="n">pass_value</span><span class="p">,</span> <span class="n">tolerance</span><span class="o">=</span><span class="n">tolerance</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">bigquery_conn_id</span> <span class="o">=</span> <span class="n">bigquery_conn_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_sql</span> <span class="o">=</span> <span class="n">use_legacy_sql</span>
<div class="viewcode-block" id="BigQueryValueCheckOperator.get_db_hook"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/bigquery_check_operator/index.html#airflow.contrib.operators.bigquery_check_operator.BigQueryValueCheckOperator.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="k">return</span> <span class="n">BigQueryHook</span><span class="p">(</span><span class="n">bigquery_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">bigquery_conn_id</span><span class="p">,</span>
<span class="n">use_legacy_sql</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_sql</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="BigQueryIntervalCheckOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/bigquery_check_operator/index.html#airflow.contrib.operators.bigquery_check_operator.BigQueryIntervalCheckOperator">[docs]</a><span class="k">class</span> <span class="nc">BigQueryIntervalCheckOperator</span><span class="p">(</span><span class="n">IntervalCheckOperator</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"> This method constructs a query like so ::</span>
<span class="sd"> SELECT {metrics_threshold_dict_key} FROM {table}</span>
<span class="sd"> WHERE {date_filter_column}=&lt;date&gt;</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, for</span>
<span class="sd"> example &#39;COUNT(*)&#39;: 1.5 would require a 50 percent or less difference</span>
<span class="sd"> between the current day, and the prior days_back.</span>
<span class="sd"> :type metrics_threshold: dict</span>
<span class="sd"> :param use_legacy_sql: Whether to use legacy SQL (true)</span>
<span class="sd"> or standard SQL (false).</span>
<span class="sd"> :type use_legacy_sql: bool</span>
<span class="sd"> &quot;&quot;&quot;</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">bigquery_conn_id</span><span class="o">=</span><span class="s1">&#39;bigquery_default&#39;</span><span class="p">,</span>
<span class="n">use_legacy_sql</span><span class="o">=</span><span class="kc">True</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">BigQueryIntervalCheckOperator</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">table</span><span class="o">=</span><span class="n">table</span><span class="p">,</span> <span class="n">metrics_thresholds</span><span class="o">=</span><span class="n">metrics_thresholds</span><span class="p">,</span>
<span class="n">date_filter_column</span><span class="o">=</span><span class="n">date_filter_column</span><span class="p">,</span> <span class="n">days_back</span><span class="o">=</span><span class="n">days_back</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">bigquery_conn_id</span> <span class="o">=</span> <span class="n">bigquery_conn_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_sql</span> <span class="o">=</span> <span class="n">use_legacy_sql</span>
<div class="viewcode-block" id="BigQueryIntervalCheckOperator.get_db_hook"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/bigquery_check_operator/index.html#airflow.contrib.operators.bigquery_check_operator.BigQueryIntervalCheckOperator.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="k">return</span> <span class="n">BigQueryHook</span><span class="p">(</span><span class="n">bigquery_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">bigquery_conn_id</span><span class="p">,</span>
<span class="n">use_legacy_sql</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_sql</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>