Google Git
Sign in
apache / airflow-site / f81e48aadee354653679693fa54b04ac42d24bfd / . / docs-archive / 1.10.3 / _modules / airflow / operators / python_operator.html
blob: 7531300b411bb8ebacff1c049aa6ba36e495c31e [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.operators.python_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.operators</a> &raquo;</li>
<li>airflow.operators.python_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.python_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">import</span> <span class="nn">inspect</span>
<span class="kn">import</span> <span class="nn">os</span>
<span class="kn">import</span> <span class="nn">pickle</span>
<span class="kn">import</span> <span class="nn">subprocess</span>
<span class="kn">import</span> <span class="nn">sys</span>
<span class="kn">import</span> <span class="nn">types</span>
<span class="kn">from</span> <span class="nn">builtins</span> <span class="k">import</span> <span class="nb">str</span>
<span class="kn">from</span> <span class="nn">textwrap</span> <span class="k">import</span> <span class="n">dedent</span>
<span class="kn">import</span> <span class="nn">dill</span>
<span class="kn">import</span> <span class="nn">six</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.models</span> <span class="k">import</span> <span class="n">BaseOperator</span>
<span class="kn">from</span> <span class="nn">airflow.models.skipmixin</span> <span class="k">import</span> <span class="n">SkipMixin</span>
<span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="k">import</span> <span class="n">apply_defaults</span>
<span class="kn">from</span> <span class="nn">airflow.utils.file</span> <span class="k">import</span> <span class="n">TemporaryDirectory</span>
<span class="kn">from</span> <span class="nn">airflow.utils.operator_helpers</span> <span class="k">import</span> <span class="n">context_to_airflow_vars</span>
<div class="viewcode-block" id="PythonOperator"><a class="viewcode-back" href="../../../_api/airflow/operators/python_operator/index.html#airflow.operators.python_operator.PythonOperator">[docs]</a><span class="k">class</span> <span class="nc">PythonOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Executes a Python callable</span>
<span class="sd"> .. seealso::</span>
<span class="sd"> For more information on how to use this operator, take a look at the guide:</span>
<span class="sd"> :ref:`howto/operator:PythonOperator`</span>
<span class="sd"> :param python_callable: A reference to an object that is callable</span>
<span class="sd"> :type python_callable: python callable</span>
<span class="sd"> :param op_kwargs: a dictionary of keyword arguments that will get unpacked</span>
<span class="sd"> in your function</span>
<span class="sd"> :type op_kwargs: dict (templated)</span>
<span class="sd"> :param op_args: a list of positional arguments that will get unpacked when</span>
<span class="sd"> calling your callable</span>
<span class="sd"> :type op_args: list (templated)</span>
<span class="sd"> :param provide_context: if set to true, Airflow will pass a set of</span>
<span class="sd"> keyword arguments that can be used in your function. This set of</span>
<span class="sd"> kwargs correspond exactly to what you can use in your jinja</span>
<span class="sd"> templates. For this to work, you need to define `**kwargs` in your</span>
<span class="sd"> function header.</span>
<span class="sd"> :type provide_context: bool</span>
<span class="sd"> :param templates_dict: a dictionary where the values are templates that</span>
<span class="sd"> will get templated by the Airflow engine sometime between</span>
<span class="sd"> ``__init__`` and ``execute`` takes place and are made available</span>
<span class="sd"> in your callable&#39;s context after the template has been applied. (templated)</span>
<span class="sd"> :type templates_dict: dict[str]</span>
<span class="sd"> :param templates_exts: a list of file extensions to resolve while</span>
<span class="sd"> processing templated fields, for examples ``[&#39;.sql&#39;, &#39;.hql&#39;]``</span>
<span class="sd"> :type templates_exts: list[str]</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="PythonOperator.template_fields"><a class="viewcode-back" href="../../../_api/airflow/operators/python_operator/index.html#airflow.operators.python_operator.PythonOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;templates_dict&#39;</span><span class="p">,</span> <span class="s1">&#39;op_args&#39;</span><span class="p">,</span> <span class="s1">&#39;op_kwargs&#39;</span><span class="p">)</span></div>
<div class="viewcode-block" id="PythonOperator.ui_color"><a class="viewcode-back" href="../../../_api/airflow/operators/python_operator/index.html#airflow.operators.python_operator.PythonOperator.ui_color">[docs]</a> <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">&#39;#ffefeb&#39;</span></div>
<span class="c1"># since we won&#39;t mutate the arguments, we should just do the shallow copy</span>
<span class="c1"># there are some cases we can&#39;t deepcopy the objects(e.g protobuf).</span>
<div class="viewcode-block" id="PythonOperator.shallow_copy_attrs"><a class="viewcode-back" href="../../../_api/airflow/operators/python_operator/index.html#airflow.operators.python_operator.PythonOperator.shallow_copy_attrs">[docs]</a> <span class="n">shallow_copy_attrs</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;python_callable&#39;</span><span class="p">,</span> <span class="s1">&#39;op_kwargs&#39;</span><span class="p">,)</span></div>
<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">python_callable</span><span class="p">,</span>
<span class="n">op_args</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">op_kwargs</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">provide_context</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">templates_dict</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">templates_exts</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">PythonOperator</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="k">if</span> <span class="ow">not</span> <span class="n">callable</span><span class="p">(</span><span class="n">python_callable</span><span class="p">):</span>
<span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">&#39;`python_callable` param must be callable&#39;</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">python_callable</span> <span class="o">=</span> <span class="n">python_callable</span>
<span class="bp">self</span><span class="o">.</span><span class="n">op_args</span> <span class="o">=</span> <span class="n">op_args</span> <span class="ow">or</span> <span class="p">[]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">op_kwargs</span> <span class="o">=</span> <span class="n">op_kwargs</span> <span class="ow">or</span> <span class="p">{}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">provide_context</span> <span class="o">=</span> <span class="n">provide_context</span>
<span class="bp">self</span><span class="o">.</span><span class="n">templates_dict</span> <span class="o">=</span> <span class="n">templates_dict</span>
<span class="k">if</span> <span class="n">templates_exts</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">template_ext</span> <span class="o">=</span> <span class="n">templates_exts</span>
<div class="viewcode-block" id="PythonOperator.execute"><a class="viewcode-back" href="../../../_api/airflow/operators/python_operator/index.html#airflow.operators.python_operator.PythonOperator.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="c1"># Export context to make it available for callables to use.</span>
<span class="n">airflow_context_vars</span> <span class="o">=</span> <span class="n">context_to_airflow_vars</span><span class="p">(</span><span class="n">context</span><span class="p">,</span> <span class="n">in_env_var_format</span><span class="o">=</span><span class="kc">True</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">&quot;Exporting the following env vars:</span><span class="se">\n</span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span>
<span class="s1">&#39;</span><span class="se">\n</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="s2">&quot;</span><span class="si">{}</span><span class="s2">=</span><span class="si">{}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="p">)</span>
<span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">airflow_context_vars</span><span class="o">.</span><span class="n">items</span><span class="p">()]))</span>
<span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">airflow_context_vars</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">provide_context</span><span class="p">:</span>
<span class="n">context</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">op_kwargs</span><span class="p">)</span>
<span class="n">context</span><span class="p">[</span><span class="s1">&#39;templates_dict&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">templates_dict</span>
<span class="bp">self</span><span class="o">.</span><span class="n">op_kwargs</span> <span class="o">=</span> <span class="n">context</span>
<span class="n">return_value</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">execute_callable</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">&quot;Done. Returned value was: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">return_value</span><span class="p">)</span>
<span class="k">return</span> <span class="n">return_value</span></div>
<div class="viewcode-block" id="PythonOperator.execute_callable"><a class="viewcode-back" href="../../../_api/airflow/operators/python_operator/index.html#airflow.operators.python_operator.PythonOperator.execute_callable">[docs]</a> <span class="k">def</span> <span class="nf">execute_callable</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">python_callable</span><span class="p">(</span><span class="o">*</span><span class="bp">self</span><span class="o">.</span><span class="n">op_args</span><span class="p">,</span> <span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">op_kwargs</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="BranchPythonOperator"><a class="viewcode-back" href="../../../_api/airflow/operators/python_operator/index.html#airflow.operators.python_operator.BranchPythonOperator">[docs]</a><span class="k">class</span> <span class="nc">BranchPythonOperator</span><span class="p">(</span><span class="n">PythonOperator</span><span class="p">,</span> <span class="n">SkipMixin</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Allows a workflow to &quot;branch&quot; or follow a path following the execution</span>
<span class="sd"> of this task.</span>
<span class="sd"> It derives the PythonOperator and expects a Python function that returns</span>
<span class="sd"> a single task_id or list of task_ids to follow. The task_id(s) returned</span>
<span class="sd"> should point to a task directly downstream from {self}. All other &quot;branches&quot;</span>
<span class="sd"> or directly downstream tasks are marked with a state of ``skipped`` so that</span>
<span class="sd"> these paths can&#39;t move forward. The ``skipped`` states are propagated</span>
<span class="sd"> downstream to allow for the DAG state to fill up and the DAG run&#39;s state</span>
<span class="sd"> to be inferred.</span>
<span class="sd"> Note that using tasks with ``depends_on_past=True`` downstream from</span>
<span class="sd"> ``BranchPythonOperator`` is logically unsound as ``skipped`` status</span>
<span class="sd"> will invariably lead to block tasks that depend on their past successes.</span>
<span class="sd"> ``skipped`` states propagates where all directly upstream tasks are</span>
<span class="sd"> ``skipped``.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="BranchPythonOperator.execute"><a class="viewcode-back" href="../../../_api/airflow/operators/python_operator/index.html#airflow.operators.python_operator.BranchPythonOperator.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="n">branch</span> <span class="o">=</span> <span class="nb">super</span><span class="p">(</span><span class="n">BranchPythonOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">context</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">branch</span><span class="p">,</span> <span class="n">six</span><span class="o">.</span><span class="n">string_types</span><span class="p">):</span>
<span class="n">branch</span> <span class="o">=</span> <span class="p">[</span><span class="n">branch</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">&quot;Following branch </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">branch</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">&quot;Marking other directly downstream tasks as skipped&quot;</span><span class="p">)</span>
<span class="n">downstream_tasks</span> <span class="o">=</span> <span class="n">context</span><span class="p">[</span><span class="s1">&#39;task&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">downstream_list</span>
<span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">&quot;Downstream task_ids </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">downstream_tasks</span><span class="p">)</span>
<span class="k">if</span> <span class="n">downstream_tasks</span><span class="p">:</span>
<span class="c1"># Also check downstream tasks of the branch task. In case the task to skip</span>
<span class="c1"># is a downstream task of the branch task, we exclude it from skipping.</span>
<span class="n">branch_downstream_task_ids</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span>
<span class="k">for</span> <span class="n">b</span> <span class="ow">in</span> <span class="n">branch</span><span class="p">:</span>
<span class="n">branch_downstream_task_ids</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">context</span><span class="p">[</span><span class="s2">&quot;dag&quot;</span><span class="p">]</span><span class="o">.</span>
<span class="n">get_task</span><span class="p">(</span><span class="n">b</span><span class="p">)</span><span class="o">.</span>
<span class="n">get_flat_relative_ids</span><span class="p">(</span><span class="n">upstream</span><span class="o">=</span><span class="kc">False</span><span class="p">))</span>
<span class="n">skip_tasks</span> <span class="o">=</span> <span class="p">[</span><span class="n">t</span>
<span class="k">for</span> <span class="n">t</span> <span class="ow">in</span> <span class="n">downstream_tasks</span>
<span class="k">if</span> <span class="n">t</span><span class="o">.</span><span class="n">task_id</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">branch</span> <span class="ow">and</span>
<span class="n">t</span><span class="o">.</span><span class="n">task_id</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">branch_downstream_task_ids</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">skip</span><span class="p">(</span><span class="n">context</span><span class="p">[</span><span class="s1">&#39;dag_run&#39;</span><span class="p">],</span> <span class="n">context</span><span class="p">[</span><span class="s1">&#39;ti&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">execution_date</span><span class="p">,</span> <span class="n">skip_tasks</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">&quot;Done.&quot;</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="ShortCircuitOperator"><a class="viewcode-back" href="../../../_api/airflow/operators/python_operator/index.html#airflow.operators.python_operator.ShortCircuitOperator">[docs]</a><span class="k">class</span> <span class="nc">ShortCircuitOperator</span><span class="p">(</span><span class="n">PythonOperator</span><span class="p">,</span> <span class="n">SkipMixin</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Allows a workflow to continue only if a condition is met. Otherwise, the</span>
<span class="sd"> workflow &quot;short-circuits&quot; and downstream tasks are skipped.</span>
<span class="sd"> The ShortCircuitOperator is derived from the PythonOperator. It evaluates a</span>
<span class="sd"> condition and short-circuits the workflow if the condition is False. Any</span>
<span class="sd"> downstream tasks are marked with a state of &quot;skipped&quot;. If the condition is</span>
<span class="sd"> True, downstream tasks proceed as normal.</span>
<span class="sd"> The condition is determined by the result of `python_callable`.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="ShortCircuitOperator.execute"><a class="viewcode-back" href="../../../_api/airflow/operators/python_operator/index.html#airflow.operators.python_operator.ShortCircuitOperator.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="n">condition</span> <span class="o">=</span> <span class="nb">super</span><span class="p">(</span><span class="n">ShortCircuitOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">context</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">&quot;Condition result is </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">condition</span><span class="p">)</span>
<span class="k">if</span> <span class="n">condition</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">&#39;Proceeding with downstream tasks...&#39;</span><span class="p">)</span>
<span class="k">return</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">&#39;Skipping downstream tasks...&#39;</span><span class="p">)</span>
<span class="n">downstream_tasks</span> <span class="o">=</span> <span class="n">context</span><span class="p">[</span><span class="s1">&#39;task&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">get_flat_relatives</span><span class="p">(</span><span class="n">upstream</span><span class="o">=</span><span class="kc">False</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">debug</span><span class="p">(</span><span class="s2">&quot;Downstream task_ids </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">downstream_tasks</span><span class="p">)</span>
<span class="k">if</span> <span class="n">downstream_tasks</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">skip</span><span class="p">(</span><span class="n">context</span><span class="p">[</span><span class="s1">&#39;dag_run&#39;</span><span class="p">],</span> <span class="n">context</span><span class="p">[</span><span class="s1">&#39;ti&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">execution_date</span><span class="p">,</span> <span class="n">downstream_tasks</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">&quot;Done.&quot;</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="PythonVirtualenvOperator"><a class="viewcode-back" href="../../../_api/airflow/operators/python_operator/index.html#airflow.operators.python_operator.PythonVirtualenvOperator">[docs]</a><span class="k">class</span> <span class="nc">PythonVirtualenvOperator</span><span class="p">(</span><span class="n">PythonOperator</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Allows one to run a function in a virtualenv that is created and destroyed</span>
<span class="sd"> automatically (with certain caveats).</span>
<span class="sd"> The function must be defined using def, and not be</span>
<span class="sd"> part of a class. All imports must happen inside the function</span>
<span class="sd"> and no variables outside of the scope may be referenced. A global scope</span>
<span class="sd"> variable named virtualenv_string_args will be available (populated by</span>
<span class="sd"> string_args). In addition, one can pass stuff through op_args and op_kwargs, and one</span>
<span class="sd"> can use a return value.</span>
<span class="sd"> Note that if your virtualenv runs in a different Python major version than Airflow,</span>
<span class="sd"> you cannot use return values, op_args, or op_kwargs. You can use string_args though.</span>
<span class="sd"> :param python_callable: A python function with no references to outside variables,</span>
<span class="sd"> defined with def, which will be run in a virtualenv</span>
<span class="sd"> :type python_callable: function</span>
<span class="sd"> :param requirements: A list of requirements as specified in a pip install command</span>
<span class="sd"> :type requirements: list[str]</span>
<span class="sd"> :param python_version: The Python version to run the virtualenv with. Note that</span>
<span class="sd"> both 2 and 2.7 are acceptable forms.</span>
<span class="sd"> :type python_version: str</span>
<span class="sd"> :param use_dill: Whether to use dill to serialize</span>
<span class="sd"> the args and result (pickle is default). This allow more complex types</span>
<span class="sd"> but requires you to include dill in your requirements.</span>
<span class="sd"> :type use_dill: bool</span>
<span class="sd"> :param system_site_packages: Whether to include</span>
<span class="sd"> system_site_packages in your virtualenv.</span>
<span class="sd"> See virtualenv documentation for more information.</span>
<span class="sd"> :type system_site_packages: bool</span>
<span class="sd"> :param op_args: A list of positional arguments to pass to python_callable.</span>
<span class="sd"> :type op_kwargs: list</span>
<span class="sd"> :param op_kwargs: A dict of keyword arguments to pass to python_callable.</span>
<span class="sd"> :type op_kwargs: dict</span>
<span class="sd"> :param provide_context: if set to true, Airflow will pass a set of</span>
<span class="sd"> keyword arguments that can be used in your function. This set of</span>
<span class="sd"> kwargs correspond exactly to what you can use in your jinja</span>
<span class="sd"> templates. For this to work, you need to define `**kwargs` in your</span>
<span class="sd"> function header.</span>
<span class="sd"> :type provide_context: bool</span>
<span class="sd"> :param string_args: Strings that are present in the global var virtualenv_string_args,</span>
<span class="sd"> available to python_callable at runtime as a list[str]. Note that args are split</span>
<span class="sd"> by newline.</span>
<span class="sd"> :type string_args: list[str]</span>
<span class="sd"> :param templates_dict: a dictionary where the values are templates that</span>
<span class="sd"> will get templated by the Airflow engine sometime between</span>
<span class="sd"> ``__init__`` and ``execute`` takes place and are made available</span>
<span class="sd"> in your callable&#39;s context after the template has been applied</span>
<span class="sd"> :type templates_dict: dict of str</span>
<span class="sd"> :param templates_exts: a list of file extensions to resolve while</span>
<span class="sd"> processing templated fields, for examples ``[&#39;.sql&#39;, &#39;.hql&#39;]``</span>
<span class="sd"> :type templates_exts: list[str]</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">python_callable</span><span class="p">,</span>
<span class="n">requirements</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">python_version</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">use_dill</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">system_site_packages</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">op_args</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">op_kwargs</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">provide_context</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">string_args</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">templates_dict</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">templates_exts</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">PythonVirtualenvOperator</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">python_callable</span><span class="o">=</span><span class="n">python_callable</span><span class="p">,</span>
<span class="n">op_args</span><span class="o">=</span><span class="n">op_args</span><span class="p">,</span>
<span class="n">op_kwargs</span><span class="o">=</span><span class="n">op_kwargs</span><span class="p">,</span>
<span class="n">templates_dict</span><span class="o">=</span><span class="n">templates_dict</span><span class="p">,</span>
<span class="n">templates_exts</span><span class="o">=</span><span class="n">templates_exts</span><span class="p">,</span>
<span class="n">provide_context</span><span class="o">=</span><span class="n">provide_context</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">requirements</span> <span class="o">=</span> <span class="n">requirements</span> <span class="ow">or</span> <span class="p">[]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">string_args</span> <span class="o">=</span> <span class="n">string_args</span> <span class="ow">or</span> <span class="p">[]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">python_version</span> <span class="o">=</span> <span class="n">python_version</span>
<span class="bp">self</span><span class="o">.</span><span class="n">use_dill</span> <span class="o">=</span> <span class="n">use_dill</span>
<span class="bp">self</span><span class="o">.</span><span class="n">system_site_packages</span> <span class="o">=</span> <span class="n">system_site_packages</span>
<span class="c1"># check that dill is present if needed</span>
<span class="n">dill_in_requirements</span> <span class="o">=</span> <span class="nb">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">x</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">&#39;dill&#39;</span><span class="p">),</span>
<span class="bp">self</span><span class="o">.</span><span class="n">requirements</span><span class="p">)</span>
<span class="k">if</span> <span class="p">(</span><span class="ow">not</span> <span class="n">system_site_packages</span><span class="p">)</span> <span class="ow">and</span> <span class="n">use_dill</span> <span class="ow">and</span> <span class="ow">not</span> <span class="nb">any</span><span class="p">(</span><span class="n">dill_in_requirements</span><span class="p">):</span>
<span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">&#39;If using dill, dill must be in the environment &#39;</span> <span class="o">+</span>
<span class="s1">&#39;either via system_site_packages or requirements&#39;</span><span class="p">)</span>
<span class="c1"># check that a function is passed, and that it is not a lambda</span>
<span class="k">if</span> <span class="p">(</span><span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">python_callable</span><span class="p">,</span>
<span class="n">types</span><span class="o">.</span><span class="n">FunctionType</span><span class="p">)</span> <span class="ow">or</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">python_callable</span><span class="o">.</span><span class="vm">__name__</span> <span class="o">==</span>
<span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="mi">0</span><span class="p">)</span><span class="o">.</span><span class="vm">__name__</span><span class="p">)):</span>
<span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">&#39;</span><span class="si">{}</span><span class="s1"> only supports functions for python_callable arg&#39;</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">)</span>
<span class="c1"># check that args are passed iff python major version matches</span>
<span class="k">if</span> <span class="p">(</span><span class="n">python_version</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span>
<span class="nb">str</span><span class="p">(</span><span class="n">python_version</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span> <span class="o">!=</span> <span class="nb">str</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">version_info</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> <span class="ow">and</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_pass_op_args</span><span class="p">()):</span>
<span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s2">&quot;Passing op_args or op_kwargs is not supported across &quot;</span>
<span class="s2">&quot;different Python major versions &quot;</span>
<span class="s2">&quot;for PythonVirtualenvOperator. &quot;</span>
<span class="s2">&quot;Please use string_args.&quot;</span><span class="p">)</span>
<div class="viewcode-block" id="PythonVirtualenvOperator.execute_callable"><a class="viewcode-back" href="../../../_api/airflow/operators/python_operator/index.html#airflow.operators.python_operator.PythonVirtualenvOperator.execute_callable">[docs]</a> <span class="k">def</span> <span class="nf">execute_callable</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">with</span> <span class="n">TemporaryDirectory</span><span class="p">(</span><span class="n">prefix</span><span class="o">=</span><span class="s1">&#39;venv&#39;</span><span class="p">)</span> <span class="k">as</span> <span class="n">tmp_dir</span><span class="p">:</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">templates_dict</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">op_kwargs</span><span class="p">[</span><span class="s1">&#39;templates_dict&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">templates_dict</span>
<span class="c1"># generate filenames</span>
<span class="n">input_filename</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">tmp_dir</span><span class="p">,</span> <span class="s1">&#39;script.in&#39;</span><span class="p">)</span>
<span class="n">output_filename</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">tmp_dir</span><span class="p">,</span> <span class="s1">&#39;script.out&#39;</span><span class="p">)</span>
<span class="n">string_args_filename</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">tmp_dir</span><span class="p">,</span> <span class="s1">&#39;string_args.txt&#39;</span><span class="p">)</span>
<span class="n">script_filename</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">tmp_dir</span><span class="p">,</span> <span class="s1">&#39;script.py&#39;</span><span class="p">)</span>
<span class="c1"># set up virtualenv</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_execute_in_subprocess</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_generate_virtualenv_cmd</span><span class="p">(</span><span class="n">tmp_dir</span><span class="p">))</span>
<span class="n">cmd</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_generate_pip_install_cmd</span><span class="p">(</span><span class="n">tmp_dir</span><span class="p">)</span>
<span class="k">if</span> <span class="n">cmd</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_execute_in_subprocess</span><span class="p">(</span><span class="n">cmd</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_write_args</span><span class="p">(</span><span class="n">input_filename</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_write_script</span><span class="p">(</span><span class="n">script_filename</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_write_string_args</span><span class="p">(</span><span class="n">string_args_filename</span><span class="p">)</span>
<span class="c1"># execute command in virtualenv</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_execute_in_subprocess</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_generate_python_cmd</span><span class="p">(</span><span class="n">tmp_dir</span><span class="p">,</span>
<span class="n">script_filename</span><span class="p">,</span>
<span class="n">input_filename</span><span class="p">,</span>
<span class="n">output_filename</span><span class="p">,</span>
<span class="n">string_args_filename</span><span class="p">))</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_read_result</span><span class="p">(</span><span class="n">output_filename</span><span class="p">)</span></div>
<div class="viewcode-block" id="PythonVirtualenvOperator._pass_op_args"><a class="viewcode-back" href="../../../_api/airflow/operators/python_operator/index.html#airflow.operators.python_operator.PythonVirtualenvOperator._pass_op_args">[docs]</a> <span class="k">def</span> <span class="nf">_pass_op_args</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="c1"># we should only pass op_args if any are given to us</span>
<span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">op_args</span><span class="p">)</span> <span class="o">+</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">op_kwargs</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</span></div>
<div class="viewcode-block" id="PythonVirtualenvOperator._execute_in_subprocess"><a class="viewcode-back" href="../../../_api/airflow/operators/python_operator/index.html#airflow.operators.python_operator.PythonVirtualenvOperator._execute_in_subprocess">[docs]</a> <span class="k">def</span> <span class="nf">_execute_in_subprocess</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">cmd</span><span class="p">):</span>
<span class="k">try</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">&quot;Executing cmd</span><span class="se">\n</span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">cmd</span><span class="p">)</span>
<span class="n">output</span> <span class="o">=</span> <span class="n">subprocess</span><span class="o">.</span><span class="n">check_output</span><span class="p">(</span><span class="n">cmd</span><span class="p">,</span>
<span class="n">stderr</span><span class="o">=</span><span class="n">subprocess</span><span class="o">.</span><span class="n">STDOUT</span><span class="p">,</span>
<span class="n">close_fds</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="k">if</span> <span class="n">output</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">&quot;Got output</span><span class="se">\n</span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">output</span><span class="p">)</span>
<span class="k">except</span> <span class="n">subprocess</span><span class="o">.</span><span class="n">CalledProcessError</span> <span class="k">as</span> <span class="n">e</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">&quot;Got error output</span><span class="se">\n</span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">e</span><span class="o">.</span><span class="n">output</span><span class="p">)</span>
<span class="k">raise</span></div>
<div class="viewcode-block" id="PythonVirtualenvOperator._write_string_args"><a class="viewcode-back" href="../../../_api/airflow/operators/python_operator/index.html#airflow.operators.python_operator.PythonVirtualenvOperator._write_string_args">[docs]</a> <span class="k">def</span> <span class="nf">_write_string_args</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">filename</span><span class="p">):</span>
<span class="c1"># writes string_args to a file, which are read line by line</span>
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">filename</span><span class="p">,</span> <span class="s1">&#39;w&#39;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
<span class="n">f</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="s1">&#39;</span><span class="se">\n</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="nb">map</span><span class="p">(</span><span class="nb">str</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">string_args</span><span class="p">)))</span></div>
<div class="viewcode-block" id="PythonVirtualenvOperator._write_args"><a class="viewcode-back" href="../../../_api/airflow/operators/python_operator/index.html#airflow.operators.python_operator.PythonVirtualenvOperator._write_args">[docs]</a> <span class="k">def</span> <span class="nf">_write_args</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">input_filename</span><span class="p">):</span>
<span class="c1"># serialize args to file</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_pass_op_args</span><span class="p">():</span>
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">input_filename</span><span class="p">,</span> <span class="s1">&#39;wb&#39;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
<span class="n">arg_dict</span> <span class="o">=</span> <span class="p">({</span><span class="s1">&#39;args&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">op_args</span><span class="p">,</span> <span class="s1">&#39;kwargs&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">op_kwargs</span><span class="p">})</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_dill</span><span class="p">:</span>
<span class="n">dill</span><span class="o">.</span><span class="n">dump</span><span class="p">(</span><span class="n">arg_dict</span><span class="p">,</span> <span class="n">f</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">pickle</span><span class="o">.</span><span class="n">dump</span><span class="p">(</span><span class="n">arg_dict</span><span class="p">,</span> <span class="n">f</span><span class="p">)</span></div>
<div class="viewcode-block" id="PythonVirtualenvOperator._read_result"><a class="viewcode-back" href="../../../_api/airflow/operators/python_operator/index.html#airflow.operators.python_operator.PythonVirtualenvOperator._read_result">[docs]</a> <span class="k">def</span> <span class="nf">_read_result</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">output_filename</span><span class="p">):</span>
<span class="k">if</span> <span class="n">os</span><span class="o">.</span><span class="n">stat</span><span class="p">(</span><span class="n">output_filename</span><span class="p">)</span><span class="o">.</span><span class="n">st_size</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="k">return</span> <span class="kc">None</span>
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">output_filename</span><span class="p">,</span> <span class="s1">&#39;rb&#39;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
<span class="k">try</span><span class="p">:</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_dill</span><span class="p">:</span>
<span class="k">return</span> <span class="n">dill</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">f</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="n">pickle</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">f</span><span class="p">)</span>
<span class="k">except</span> <span class="ne">ValueError</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">error</span><span class="p">(</span><span class="s2">&quot;Error deserializing result. &quot;</span>
<span class="s2">&quot;Note that result deserialization &quot;</span>
<span class="s2">&quot;is not supported across major Python versions.&quot;</span><span class="p">)</span>
<span class="k">raise</span></div>
<div class="viewcode-block" id="PythonVirtualenvOperator._write_script"><a class="viewcode-back" href="../../../_api/airflow/operators/python_operator/index.html#airflow.operators.python_operator.PythonVirtualenvOperator._write_script">[docs]</a> <span class="k">def</span> <span class="nf">_write_script</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">script_filename</span><span class="p">):</span>
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">script_filename</span><span class="p">,</span> <span class="s1">&#39;w&#39;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
<span class="n">python_code</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_generate_python_code</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">debug</span><span class="p">(</span><span class="s1">&#39;Writing code to file</span><span class="se">\n</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">python_code</span><span class="p">))</span>
<span class="n">f</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="n">python_code</span><span class="p">)</span></div>
<div class="viewcode-block" id="PythonVirtualenvOperator._generate_virtualenv_cmd"><a class="viewcode-back" href="../../../_api/airflow/operators/python_operator/index.html#airflow.operators.python_operator.PythonVirtualenvOperator._generate_virtualenv_cmd">[docs]</a> <span class="k">def</span> <span class="nf">_generate_virtualenv_cmd</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tmp_dir</span><span class="p">):</span>
<span class="n">cmd</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;virtualenv&#39;</span><span class="p">,</span> <span class="n">tmp_dir</span><span class="p">]</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">system_site_packages</span><span class="p">:</span>
<span class="n">cmd</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s1">&#39;--system-site-packages&#39;</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">python_version</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">cmd</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s1">&#39;--python=python</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="bp">self</span><span class="o">.</span><span class="n">python_version</span><span class="p">))</span>
<span class="k">return</span> <span class="n">cmd</span></div>
<div class="viewcode-block" id="PythonVirtualenvOperator._generate_pip_install_cmd"><a class="viewcode-back" href="../../../_api/airflow/operators/python_operator/index.html#airflow.operators.python_operator.PythonVirtualenvOperator._generate_pip_install_cmd">[docs]</a> <span class="k">def</span> <span class="nf">_generate_pip_install_cmd</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tmp_dir</span><span class="p">):</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">requirements</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="k">return</span> <span class="p">[]</span>
<span class="k">else</span><span class="p">:</span>
<span class="c1"># direct path alleviates need to activate</span>
<span class="n">cmd</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;</span><span class="si">{}</span><span class="s1">/bin/pip&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">tmp_dir</span><span class="p">),</span> <span class="s1">&#39;install&#39;</span><span class="p">]</span>
<span class="k">return</span> <span class="n">cmd</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">requirements</span></div>
<span class="nd">@staticmethod</span>
<div class="viewcode-block" id="PythonVirtualenvOperator._generate_python_cmd"><a class="viewcode-back" href="../../../_api/airflow/operators/python_operator/index.html#airflow.operators.python_operator.PythonVirtualenvOperator._generate_python_cmd">[docs]</a> <span class="k">def</span> <span class="nf">_generate_python_cmd</span><span class="p">(</span><span class="n">tmp_dir</span><span class="p">,</span> <span class="n">script_filename</span><span class="p">,</span>
<span class="n">input_filename</span><span class="p">,</span> <span class="n">output_filename</span><span class="p">,</span> <span class="n">string_args_filename</span><span class="p">):</span>
<span class="c1"># direct path alleviates need to activate</span>
<span class="k">return</span> <span class="p">[</span><span class="s1">&#39;</span><span class="si">{}</span><span class="s1">/bin/python&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">tmp_dir</span><span class="p">),</span> <span class="n">script_filename</span><span class="p">,</span>
<span class="n">input_filename</span><span class="p">,</span> <span class="n">output_filename</span><span class="p">,</span> <span class="n">string_args_filename</span><span class="p">]</span></div>
<div class="viewcode-block" id="PythonVirtualenvOperator._generate_python_code"><a class="viewcode-back" href="../../../_api/airflow/operators/python_operator/index.html#airflow.operators.python_operator.PythonVirtualenvOperator._generate_python_code">[docs]</a> <span class="k">def</span> <span class="nf">_generate_python_code</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_dill</span><span class="p">:</span>
<span class="n">pickling_library</span> <span class="o">=</span> <span class="s1">&#39;dill&#39;</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">pickling_library</span> <span class="o">=</span> <span class="s1">&#39;pickle&#39;</span>
<span class="n">fn</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">python_callable</span>
<span class="c1"># dont try to read pickle if we didnt pass anything</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_pass_op_args</span><span class="p">():</span>
<span class="n">load_args_line</span> <span class="o">=</span> <span class="s1">&#39;with open(sys.argv[1], &quot;rb&quot;) as f: arg_dict = </span><span class="si">{}</span><span class="s1">.load(f)&#39;</span>\
<span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">pickling_library</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">load_args_line</span> <span class="o">=</span> <span class="s1">&#39;arg_dict = {&quot;args&quot;: [], &quot;kwargs&quot;: </span><span class="si">{}</span><span class="s1">}&#39;</span>
<span class="c1"># no indents in original code so we can accept</span>
<span class="c1"># any type of indents in the original function</span>
<span class="c1"># we deserialize args, call function, serialize result if necessary</span>
<span class="k">return</span> <span class="n">dedent</span><span class="p">(</span><span class="s2">&quot;&quot;&quot;</span><span class="se">\</span>
<span class="s2"> import </span><span class="si">{pickling_library}</span><span class="s2"></span>
<span class="s2"> import sys</span>
<span class="s2"> </span><span class="si">{load_args_code}</span><span class="s2"></span>
<span class="s2"> args = arg_dict[&quot;args&quot;]</span>
<span class="s2"> kwargs = arg_dict[&quot;kwargs&quot;]</span>
<span class="s2"> with open(sys.argv[3], &#39;r&#39;) as f:</span>
<span class="s2"> virtualenv_string_args = list(map(lambda x: x.strip(), list(f)))</span>
<span class="s2"> </span><span class="si">{python_callable_lines}</span><span class="s2"></span>
<span class="s2"> res = </span><span class="si">{python_callable_name}</span><span class="s2">(*args, **kwargs)</span>
<span class="s2"> with open(sys.argv[2], &#39;wb&#39;) as f:</span>
<span class="s2"> res is not None and </span><span class="si">{pickling_library}</span><span class="s2">.dump(res, f)</span>
<span class="s2"> &quot;&quot;&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">load_args_code</span><span class="o">=</span><span class="n">load_args_line</span><span class="p">,</span>
<span class="n">python_callable_lines</span><span class="o">=</span><span class="n">dedent</span><span class="p">(</span><span class="n">inspect</span><span class="o">.</span><span class="n">getsource</span><span class="p">(</span><span class="n">fn</span><span class="p">)),</span>
<span class="n">python_callable_name</span><span class="o">=</span><span class="n">fn</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span>
<span class="n">pickling_library</span><span class="o">=</span><span class="n">pickling_library</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">&quot;Done.&quot;</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>