| |
| |
| <!-- |
| Javascript to render AIRFLOW-XXX and PR references in text |
| as HTML links. |
| |
| Overrides extrahead block from sphinx_rtd_theme |
| https://www.sphinx-doc.org/en/master/templating.html |
| --> |
| |
| |
| <!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>Lineage — Airflow Documentation</title> |
| |
| |
| |
| |
| <link rel="shortcut icon" href="_static/pin_32.png"/> |
| |
| |
| |
| |
| |
| <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/jira-links.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="stylesheet" href="_static/graphviz.css" type="text/css" /> |
| <link rel="stylesheet" href="_static/exampleinclude.css" type="text/css" /> |
| <link rel="index" title="Index" href="genindex.html" /> |
| <link rel="search" title="Search" href="search.html" /> |
| <link rel="next" title="DAG Serialization" href="dag-serialization.html" /> |
| <link rel="prev" title="Kubernetes" href="kubernetes.html" /> |
| |
| <script> |
| </script> |
| <style> |
| |
| </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"> |
| 1.10.8 |
| </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 class="current"> |
| <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 Reference</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="executor/index.html">Executor</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">REST API Reference</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="errors.html">Error Tracking</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="kubernetes.html">Kubernetes</a></li> |
| <li class="toctree-l1 current"><a class="current reference internal" href="#">Lineage</a><ul> |
| <li class="toctree-l2"><a class="reference internal" href="#apache-atlas">Apache Atlas</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l1"><a class="reference internal" href="dag-serialization.html">DAG Serialization</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="best-practices.html">Best Practices</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="privacy_notice.html">Privacy Notice</a></li> |
| </ul> |
| <p class="caption"><span class="caption-text">References</span></p> |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="_api/index.html">Python API</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="configurations-ref.html">Configurations</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>Lineage</li> |
| |
| |
| <li class="wy-breadcrumbs-aside"> |
| |
| |
| <a href="_sources/lineage.rst.txt" rel="nofollow"> View page source</a> |
| |
| |
| </li> |
| |
| </ul> |
| |
| |
| <hr/> |
| </div> |
| <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> |
| <div itemprop="articleBody"> |
| |
| <blockquote> |
| <div></div></blockquote> |
| <div class="section" id="lineage"> |
| <h1>Lineage<a class="headerlink" href="#lineage" title="Permalink to this headline">ΒΆ</a></h1> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>Lineage support is very experimental and subject to change.</p> |
| </div> |
| <p>Airflow can help track origins of data, what happens to it and where it moves over time. This can aid having |
| audit trails and data governance, but also debugging of data flows.</p> |
| <p>Airflow tracks data by means of inlets and outlets of the tasks. Letβs work from an example and see how it |
| works.</p> |
| <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">airflow.operators.bash_operator</span> <span class="kn">import</span> <span class="n">BashOperator</span> |
| <span class="kn">from</span> <span class="nn">airflow.operators.dummy_operator</span> <span class="kn">import</span> <span class="n">DummyOperator</span> |
| <span class="kn">from</span> <span class="nn">airflow.lineage.datasets</span> <span class="kn">import</span> <span class="n">File</span> |
| <span class="kn">from</span> <span class="nn">airflow.models</span> <span class="kn">import</span> <span class="n">DAG</span> |
| <span class="kn">from</span> <span class="nn">airflow.utils.dates</span> <span class="kn">import</span> <span class="n">days_ago</span> |
| <span class="kn">from</span> <span class="nn">datetime</span> <span class="kn">import</span> <span class="n">timedelta</span> |
| |
| <span class="n">FILE_CATEGORIES</span> <span class="o">=</span> <span class="p">[</span><span class="s2">"CAT1"</span><span class="p">,</span> <span class="s2">"CAT2"</span><span class="p">,</span> <span class="s2">"CAT3"</span><span class="p">]</span> |
| |
| <span class="n">args</span> <span class="o">=</span> <span class="p">{</span> |
| <span class="s1">'owner'</span><span class="p">:</span> <span class="s1">'Airflow'</span><span class="p">,</span> |
| <span class="s1">'start_date'</span><span class="p">:</span> <span class="n">days_ago</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span> |
| <span class="p">}</span> |
| |
| <span class="n">dag</span> <span class="o">=</span> <span class="n">DAG</span><span class="p">(</span> |
| <span class="n">dag_id</span><span class="o">=</span><span class="s1">'example_lineage'</span><span class="p">,</span> <span class="n">default_args</span><span class="o">=</span><span class="n">args</span><span class="p">,</span> |
| <span class="n">schedule_interval</span><span class="o">=</span><span class="s1">'0 0 * * *'</span><span class="p">,</span> |
| <span class="n">dagrun_timeout</span><span class="o">=</span><span class="n">timedelta</span><span class="p">(</span><span class="n">minutes</span><span class="o">=</span><span class="mi">60</span><span class="p">))</span> |
| |
| <span class="n">f_final</span> <span class="o">=</span> <span class="n">File</span><span class="p">(</span><span class="s2">"/tmp/final"</span><span class="p">)</span> |
| <span class="n">run_this_last</span> <span class="o">=</span> <span class="n">DummyOperator</span><span class="p">(</span><span class="n">task_id</span><span class="o">=</span><span class="s1">'run_this_last'</span><span class="p">,</span> <span class="n">dag</span><span class="o">=</span><span class="n">dag</span><span class="p">,</span> |
| <span class="n">inlets</span><span class="o">=</span><span class="p">{</span><span class="s2">"auto"</span><span class="p">:</span> <span class="kc">True</span><span class="p">},</span> |
| <span class="n">outlets</span><span class="o">=</span><span class="p">{</span><span class="s2">"datasets"</span><span class="p">:</span> <span class="p">[</span><span class="n">f_final</span><span class="p">,]})</span> |
| |
| <span class="n">f_in</span> <span class="o">=</span> <span class="n">File</span><span class="p">(</span><span class="s2">"/tmp/whole_directory/"</span><span class="p">)</span> |
| <span class="n">outlets</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">for</span> <span class="n">file</span> <span class="ow">in</span> <span class="n">FILE_CATEGORIES</span><span class="p">:</span> |
| <span class="n">f_out</span> <span class="o">=</span> <span class="n">File</span><span class="p">(</span><span class="s2">"/tmp/</span><span class="si">{}</span><span class="s2">/{{{{ execution_date }}}}"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">file</span><span class="p">))</span> |
| <span class="n">outlets</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">f_out</span><span class="p">)</span> |
| <span class="n">run_this</span> <span class="o">=</span> <span class="n">BashOperator</span><span class="p">(</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s1">'run_me_first'</span><span class="p">,</span> <span class="n">bash_command</span><span class="o">=</span><span class="s1">'echo 1'</span><span class="p">,</span> <span class="n">dag</span><span class="o">=</span><span class="n">dag</span><span class="p">,</span> |
| <span class="n">inlets</span><span class="o">=</span><span class="p">{</span><span class="s2">"datasets"</span><span class="p">:</span> <span class="p">[</span><span class="n">f_in</span><span class="p">,]},</span> |
| <span class="n">outlets</span><span class="o">=</span><span class="p">{</span><span class="s2">"datasets"</span><span class="p">:</span> <span class="n">outlets</span><span class="p">}</span> |
| <span class="p">)</span> |
| <span class="n">run_this</span><span class="o">.</span><span class="n">set_downstream</span><span class="p">(</span><span class="n">run_this_last</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>Tasks take the parameters <code class="docutils literal notranslate"><span class="pre">inlets</span></code> and <code class="docutils literal notranslate"><span class="pre">outlets</span></code>.</p> |
| <p>Inlets can be manually defined by the following options:</p> |
| <ul class="simple"> |
| <li><p>by a list of dataset <code class="docutils literal notranslate"><span class="pre">{"datasets":</span> <span class="pre">[dataset1,</span> <span class="pre">dataset2]}</span></code></p></li> |
| <li><p>can be configured to look for outlets from upstream tasks <code class="docutils literal notranslate"><span class="pre">{"task_ids":</span> <span class="pre">["task_id1",</span> <span class="pre">"task_id2"]}</span></code></p></li> |
| <li><p>can be configured to pick up outlets from direct upstream tasks <code class="docutils literal notranslate"><span class="pre">{"auto":</span> <span class="pre">True}</span></code></p></li> |
| <li><p>a combination of them</p></li> |
| </ul> |
| <p>Outlets are defined as list of dataset <code class="docutils literal notranslate"><span class="pre">{"datasets":</span> <span class="pre">[dataset1,</span> <span class="pre">dataset2]}</span></code>. Any fields for the dataset are templated with |
| the context when the task is being executed.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>Operators can add inlets and outlets automatically if the operator supports it.</p> |
| </div> |
| <p>In the example DAG task <code class="docutils literal notranslate"><span class="pre">run_me_first</span></code> is a BashOperator that takes 3 inlets: <code class="docutils literal notranslate"><span class="pre">CAT1</span></code>, <code class="docutils literal notranslate"><span class="pre">CAT2</span></code>, <code class="docutils literal notranslate"><span class="pre">CAT3</span></code>, that are |
| generated from a list. Note that <code class="docutils literal notranslate"><span class="pre">execution_date</span></code> is a templated field and will be rendered when the task is running.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>Behind the scenes Airflow prepares the lineage metadata as part of the <code class="docutils literal notranslate"><span class="pre">pre_execute</span></code> method of a task. When the task |
| has finished execution <code class="docutils literal notranslate"><span class="pre">post_execute</span></code> is called and lineage metadata is pushed into XCOM. Thus if you are creating |
| your own operators that override this method make sure to decorate your method with <code class="docutils literal notranslate"><span class="pre">prepare_lineage</span></code> and <code class="docutils literal notranslate"><span class="pre">apply_lineage</span></code> |
| respectively.</p> |
| </div> |
| <div class="section" id="apache-atlas"> |
| <h2>Apache Atlas<a class="headerlink" href="#apache-atlas" title="Permalink to this headline">ΒΆ</a></h2> |
| <p>Airflow can send its lineage metadata to Apache Atlas. You need to enable the <code class="docutils literal notranslate"><span class="pre">atlas</span></code> backend and configure it |
| properly, e.g. in your <code class="docutils literal notranslate"><span class="pre">airflow.cfg</span></code>:</p> |
| <div class="highlight-ini notranslate"><div class="highlight"><pre><span></span><span class="k">[lineage]</span> |
| <span class="na">backend</span> <span class="o">=</span> <span class="s">airflow.lineage.backend.atlas.AtlasBackend</span> |
| |
| <span class="k">[atlas]</span> |
| <span class="na">username</span> <span class="o">=</span> <span class="s">my_username</span> |
| <span class="na">password</span> <span class="o">=</span> <span class="s">my_password</span> |
| <span class="na">host</span> <span class="o">=</span> <span class="s">host</span> |
| <span class="na">port</span> <span class="o">=</span> <span class="s">21000</span> |
| </pre></div> |
| </div> |
| <p>Please make sure to have the <code class="docutils literal notranslate"><span class="pre">atlasclient</span></code> package installed.</p> |
| </div> |
| </div> |
| |
| |
| </div> |
| |
| </div> |
| |
| |
| <footer> |
| |
| <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation"> |
| |
| <a href="dag-serialization.html" class="btn btn-neutral float-right" title="DAG Serialization" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a> |
| |
| |
| <a href="kubernetes.html" class="btn btn-neutral float-left" title="Kubernetes" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a> |
| |
| </div> |
| |
| |
| <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>. |
| <div class="footer">This page uses <a href="https://analytics.google.com/"> |
| Google Analytics</a> to collect statistics. You can disable it by blocking |
| the JavaScript coming from www.google-analytics.com. Check our |
| <a href="privacy_notice.html">Privacy Policy</a> |
| for more details. |
| </div> |
| |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| |
| |
| |
| <!-- Theme Analytics --> |
| <script> |
| (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ |
| (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o), |
| m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) |
| })(window,document,'script','https://www.google-analytics.com/analytics.js','ga'); |
| |
| ga('create', 'UA-140539454-1', 'auto'); |
| ga('send', 'pageview'); |
| </script> |
| |
| |
| |
| |
| </body> |
| </html> |