| |
| |
| <!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.mongo_to_s3 — 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.contrib.operators.mongo_to_s3</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.mongo_to_s3</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 "License");</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 "AS IS" 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">import</span> <span class="nn">json</span> |
| |
| <span class="kn">from</span> <span class="nn">airflow.contrib.hooks.mongo_hook</span> <span class="k">import</span> <span class="n">MongoHook</span> |
| <span class="kn">from</span> <span class="nn">airflow.hooks.S3_hook</span> <span class="k">import</span> <span class="n">S3Hook</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">bson</span> <span class="k">import</span> <span class="n">json_util</span> |
| |
| |
| <div class="viewcode-block" id="MongoToS3Operator"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.operators.mongo_to_s3.MongoToS3Operator">[docs]</a><span class="k">class</span> <span class="nc">MongoToS3Operator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Mongo -> S3</span> |
| <span class="sd"> A more specific baseOperator meant to move data</span> |
| <span class="sd"> from mongo via pymongo to s3 via boto</span> |
| |
| <span class="sd"> things to note</span> |
| <span class="sd"> .execute() is written to depend on .transform()</span> |
| <span class="sd"> .transform() is meant to be extended by child classes</span> |
| <span class="sd"> to perform transformations unique to those operators needs</span> |
| <span class="sd"> """</span> |
| |
| <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'s3_key'</span><span class="p">,</span> <span class="s1">'mongo_query'</span><span class="p">]</span> |
| <span class="c1"># pylint: disable=too-many-instance-attributes</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">mongo_conn_id</span><span class="p">,</span> |
| <span class="n">s3_conn_id</span><span class="p">,</span> |
| <span class="n">mongo_collection</span><span class="p">,</span> |
| <span class="n">mongo_query</span><span class="p">,</span> |
| <span class="n">s3_bucket</span><span class="p">,</span> |
| <span class="n">s3_key</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">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">MongoToS3Operator</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="c1"># Conn Ids</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">mongo_conn_id</span> <span class="o">=</span> <span class="n">mongo_conn_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">s3_conn_id</span> <span class="o">=</span> <span class="n">s3_conn_id</span> |
| <span class="c1"># Mongo Query Settings</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">mongo_db</span> <span class="o">=</span> <span class="n">mongo_db</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">mongo_collection</span> <span class="o">=</span> <span class="n">mongo_collection</span> |
| <span class="c1"># Grab query and determine if we need to run an aggregate pipeline</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">mongo_query</span> <span class="o">=</span> <span class="n">mongo_query</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">is_pipeline</span> <span class="o">=</span> <span class="kc">True</span> <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">mongo_query</span><span class="p">,</span> <span class="nb">list</span><span class="p">)</span> <span class="k">else</span> <span class="kc">False</span> |
| |
| <span class="c1"># S3 Settings</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">s3_bucket</span> <span class="o">=</span> <span class="n">s3_bucket</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">s3_key</span> <span class="o">=</span> <span class="n">s3_key</span> |
| |
| <span class="c1"># KWARGS</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">replace</span> <span class="o">=</span> <span class="n">kwargs</span><span class="o">.</span><span class="n">pop</span><span class="p">(</span><span class="s1">'replace'</span><span class="p">,</span> <span class="kc">False</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="MongoToS3Operator.execute"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.operators.mongo_to_s3.MongoToS3Operator.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="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Executed by task_instance at runtime</span> |
| <span class="sd"> """</span> |
| <span class="n">s3_conn</span> <span class="o">=</span> <span class="n">S3Hook</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">s3_conn_id</span><span class="p">)</span> |
| |
| <span class="c1"># Grab collection and execute query according to whether or not it is a pipeline</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_pipeline</span><span class="p">:</span> |
| <span class="n">results</span> <span class="o">=</span> <span class="n">MongoHook</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">mongo_conn_id</span><span class="p">)</span><span class="o">.</span><span class="n">aggregate</span><span class="p">(</span> |
| <span class="n">mongo_collection</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">mongo_collection</span><span class="p">,</span> |
| <span class="n">aggregate_query</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">mongo_query</span><span class="p">,</span> |
| <span class="n">mongo_db</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">mongo_db</span> |
| <span class="p">)</span> |
| |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">results</span> <span class="o">=</span> <span class="n">MongoHook</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">mongo_conn_id</span><span class="p">)</span><span class="o">.</span><span class="n">find</span><span class="p">(</span> |
| <span class="n">mongo_collection</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">mongo_collection</span><span class="p">,</span> |
| <span class="n">query</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">mongo_query</span><span class="p">,</span> |
| <span class="n">mongo_db</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">mongo_db</span> |
| <span class="p">)</span> |
| |
| <span class="c1"># Performs transform then stringifies the docs results into json format</span> |
| <span class="n">docs_str</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_stringify</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">results</span><span class="p">))</span> |
| |
| <span class="c1"># Load Into S3</span> |
| <span class="n">s3_conn</span><span class="o">.</span><span class="n">load_string</span><span class="p">(</span> |
| <span class="n">string_data</span><span class="o">=</span><span class="n">docs_str</span><span class="p">,</span> |
| <span class="n">key</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">s3_key</span><span class="p">,</span> |
| <span class="n">bucket_name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">s3_bucket</span><span class="p">,</span> |
| <span class="n">replace</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">replace</span> |
| <span class="p">)</span> |
| |
| <span class="k">return</span> <span class="kc">True</span></div> |
| |
| <span class="k">def</span> <span class="nf">_stringify</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">iterable</span><span class="p">,</span> <span class="n">joinable</span><span class="o">=</span><span class="s1">'</span><span class="se">\n</span><span class="s1">'</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Takes an iterable (pymongo Cursor or Array) containing dictionaries and</span> |
| <span class="sd"> returns a stringified version using python join</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">joinable</span><span class="o">.</span><span class="n">join</span><span class="p">(</span> |
| <span class="p">[</span><span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="n">doc</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="n">json_util</span><span class="o">.</span><span class="n">default</span><span class="p">)</span> <span class="k">for</span> <span class="n">doc</span> <span class="ow">in</span> <span class="n">iterable</span><span class="p">]</span> |
| <span class="p">)</span> |
| |
| <div class="viewcode-block" id="MongoToS3Operator.transform"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.operators.mongo_to_s3.MongoToS3Operator.transform">[docs]</a> <span class="k">def</span> <span class="nf">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">docs</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Processes pyMongo cursor and returns an iterable with each element being</span> |
| <span class="sd"> a JSON serializable dictionary</span> |
| |
| <span class="sd"> Base transform() assumes no processing is needed</span> |
| <span class="sd"> ie. docs is a pyMongo cursor of documents and cursor just</span> |
| <span class="sd"> needs to be passed through</span> |
| |
| <span class="sd"> Override this method for custom transformations</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">docs</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> |