blob: 536ac27268a3e578fdc3a265e7291b6aa40f6a60 [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.mongo_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 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.contrib.hooks.mongo_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.mongo_hook</h1><div class="highlight"><pre>
<span></span><span class="c1"># -*- coding: utf-8 -*-</span>
<span class="c1">#</span>
<span class="c1"># Licensed under the Apache License, Version 2.0 (the &quot;License&quot;);</span>
<span class="c1"># you may not use this file except in compliance with the License.</span>
<span class="c1"># 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, software</span>
<span class="c1"># distributed under the License is distributed on an &quot;AS IS&quot; BASIS,</span>
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
<span class="c1"># See the License for the specific language governing permissions and</span>
<span class="c1"># limitations under the License.</span>
<span class="kn">from</span> <span class="nn">ssl</span> <span class="k">import</span> <span class="n">CERT_NONE</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">pymongo</span> <span class="k">import</span> <span class="n">MongoClient</span>
<div class="viewcode-block" id="MongoHook"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.hooks.mongo_hook.MongoHook">[docs]</a><span class="k">class</span> <span class="nc">MongoHook</span><span class="p">(</span><span class="n">BaseHook</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> PyMongo Wrapper to Interact With Mongo Database</span>
<span class="sd"> Mongo Connection Documentation</span>
<span class="sd"> https://docs.mongodb.com/manual/reference/connection-string/index.html</span>
<span class="sd"> You can specify connection string options in extra field of your connection</span>
<span class="sd"> https://docs.mongodb.com/manual/reference/connection-string/index.html#connection-string-options</span>
<span class="sd"> ex.</span>
<span class="sd"> {replicaSet: test, ssl: True, connectTimeoutMS: 30000}</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">conn_type</span> <span class="o">=</span> <span class="s1">&#39;MongoDb&#39;</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">conn_id</span><span class="o">=</span><span class="s1">&#39;mongo_default&#39;</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">MongoHook</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">source</span><span class="o">=</span><span class="s1">&#39;mongo&#39;</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">mongo_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">connection</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_connection</span><span class="p">(</span><span class="n">conn_id</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">extras</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">connection</span><span class="o">.</span><span class="n">extra_dejson</span>
<span class="bp">self</span><span class="o">.</span><span class="n">client</span> <span class="o">=</span> <span class="kc">None</span>
<div class="viewcode-block" id="MongoHook.get_conn"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.hooks.mongo_hook.MongoHook.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"> Fetches PyMongo Client</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">client</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">client</span>
<span class="n">conn</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">connection</span>
<span class="n">uri</span> <span class="o">=</span> <span class="s1">&#39;mongodb://</span><span class="si">{creds}{host}{port}</span><span class="s1">/</span><span class="si">{database}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="n">creds</span><span class="o">=</span><span class="s1">&#39;</span><span class="si">{}</span><span class="s1">:</span><span class="si">{}</span><span class="s1">@&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="n">conn</span><span class="o">.</span><span class="n">login</span><span class="p">,</span> <span class="n">conn</span><span class="o">.</span><span class="n">password</span>
<span class="p">)</span> <span class="k">if</span> <span class="n">conn</span><span class="o">.</span><span class="n">login</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="k">else</span> <span class="s1">&#39;&#39;</span><span class="p">,</span>
<span class="n">host</span><span class="o">=</span><span class="n">conn</span><span class="o">.</span><span class="n">host</span><span class="p">,</span>
<span class="n">port</span><span class="o">=</span><span class="s1">&#39;&#39;</span> <span class="k">if</span> <span class="n">conn</span><span class="o">.</span><span class="n">port</span> <span class="ow">is</span> <span class="kc">None</span> <span class="k">else</span> <span class="s1">&#39;:</span><span class="si">{}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">conn</span><span class="o">.</span><span class="n">port</span><span class="p">),</span>
<span class="n">database</span><span class="o">=</span><span class="s1">&#39;&#39;</span> <span class="k">if</span> <span class="n">conn</span><span class="o">.</span><span class="n">schema</span> <span class="ow">is</span> <span class="kc">None</span> <span class="k">else</span> <span class="n">conn</span><span class="o">.</span><span class="n">schema</span>
<span class="p">)</span>
<span class="c1"># Mongo Connection Options dict that is unpacked when passed to MongoClient</span>
<span class="n">options</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">extras</span>
<span class="c1"># If we are using SSL disable requiring certs from specific hostname</span>
<span class="k">if</span> <span class="n">options</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;ssl&#39;</span><span class="p">,</span> <span class="kc">False</span><span class="p">):</span>
<span class="n">options</span><span class="o">.</span><span class="n">update</span><span class="p">({</span><span class="s1">&#39;ssl_cert_reqs&#39;</span><span class="p">:</span> <span class="n">CERT_NONE</span><span class="p">})</span>
<span class="bp">self</span><span class="o">.</span><span class="n">client</span> <span class="o">=</span> <span class="n">MongoClient</span><span class="p">(</span><span class="n">uri</span><span class="p">,</span> <span class="o">**</span><span class="n">options</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">client</span></div>
<div class="viewcode-block" id="MongoHook.get_collection"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.hooks.mongo_hook.MongoHook.get_collection">[docs]</a> <span class="k">def</span> <span class="nf">get_collection</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">mongo_collection</span><span class="p">,</span> <span class="n">mongo_db</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Fetches a mongo collection object for querying.</span>
<span class="sd"> Uses connection schema as DB unless specified.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">mongo_db</span> <span class="o">=</span> <span class="n">mongo_db</span> <span class="k">if</span> <span class="n">mongo_db</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="k">else</span> <span class="bp">self</span><span class="o">.</span><span class="n">connection</span><span class="o">.</span><span class="n">schema</span>
<span class="n">mongo_conn</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span>
<span class="k">return</span> <span class="n">mongo_conn</span><span class="o">.</span><span class="n">get_database</span><span class="p">(</span><span class="n">mongo_db</span><span class="p">)</span><span class="o">.</span><span class="n">get_collection</span><span class="p">(</span><span class="n">mongo_collection</span><span class="p">)</span></div>
<div class="viewcode-block" id="MongoHook.aggregate"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.hooks.mongo_hook.MongoHook.aggregate">[docs]</a> <span class="k">def</span> <span class="nf">aggregate</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">mongo_collection</span><span class="p">,</span> <span class="n">aggregate_query</span><span class="p">,</span> <span class="n">mongo_db</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Runs an aggregation pipeline and returns the results</span>
<span class="sd"> https://api.mongodb.com/python/current/api/pymongo/collection.html#pymongo.collection.Collection.aggregate</span>
<span class="sd"> https://api.mongodb.com/python/current/examples/aggregation.html</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">collection</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_collection</span><span class="p">(</span><span class="n">mongo_collection</span><span class="p">,</span> <span class="n">mongo_db</span><span class="o">=</span><span class="n">mongo_db</span><span class="p">)</span>
<span class="k">return</span> <span class="n">collection</span><span class="o">.</span><span class="n">aggregate</span><span class="p">(</span><span class="n">aggregate_query</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div>
<div class="viewcode-block" id="MongoHook.find"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.hooks.mongo_hook.MongoHook.find">[docs]</a> <span class="k">def</span> <span class="nf">find</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">mongo_collection</span><span class="p">,</span> <span class="n">query</span><span class="p">,</span> <span class="n">find_one</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">mongo_db</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Runs a mongo find query and returns the results</span>
<span class="sd"> https://api.mongodb.com/python/current/api/pymongo/collection.html#pymongo.collection.Collection.find</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">collection</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_collection</span><span class="p">(</span><span class="n">mongo_collection</span><span class="p">,</span> <span class="n">mongo_db</span><span class="o">=</span><span class="n">mongo_db</span><span class="p">)</span>
<span class="k">if</span> <span class="n">find_one</span><span class="p">:</span>
<span class="k">return</span> <span class="n">collection</span><span class="o">.</span><span class="n">find_one</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="n">collection</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div>
<div class="viewcode-block" id="MongoHook.insert_one"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.hooks.mongo_hook.MongoHook.insert_one">[docs]</a> <span class="k">def</span> <span class="nf">insert_one</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">mongo_collection</span><span class="p">,</span> <span class="n">doc</span><span class="p">,</span> <span class="n">mongo_db</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Inserts a single document into a mongo collection</span>
<span class="sd"> https://api.mongodb.com/python/current/api/pymongo/collection.html#pymongo.collection.Collection.insert_one</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">collection</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_collection</span><span class="p">(</span><span class="n">mongo_collection</span><span class="p">,</span> <span class="n">mongo_db</span><span class="o">=</span><span class="n">mongo_db</span><span class="p">)</span>
<span class="k">return</span> <span class="n">collection</span><span class="o">.</span><span class="n">insert_one</span><span class="p">(</span><span class="n">doc</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div>
<div class="viewcode-block" id="MongoHook.insert_many"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.hooks.mongo_hook.MongoHook.insert_many">[docs]</a> <span class="k">def</span> <span class="nf">insert_many</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">mongo_collection</span><span class="p">,</span> <span class="n">docs</span><span class="p">,</span> <span class="n">mongo_db</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Inserts many docs into a mongo collection.</span>
<span class="sd"> https://api.mongodb.com/python/current/api/pymongo/collection.html#pymongo.collection.Collection.insert_many</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">collection</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_collection</span><span class="p">(</span><span class="n">mongo_collection</span><span class="p">,</span> <span class="n">mongo_db</span><span class="o">=</span><span class="n">mongo_db</span><span class="p">)</span>
<span class="k">return</span> <span class="n">collection</span><span class="o">.</span><span class="n">insert_many</span><span class="p">(</span><span class="n">docs</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</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>