You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@airflow.apache.org by ka...@apache.org on 2018/08/27 16:26:28 UTC
[08/51] [partial] incubator-airflow-site git commit: 1.10.0
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/11437c14/_modules/airflow/operators/python_operator.html
----------------------------------------------------------------------
diff --git a/_modules/airflow/operators/python_operator.html b/_modules/airflow/operators/python_operator.html
new file mode 100644
index 0000000..fb1e29d
--- /dev/null
+++ b/_modules/airflow/operators/python_operator.html
@@ -0,0 +1,613 @@
+
+
+<!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 — Airflow Documentation</title>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
+
+
+
+
+
+ <link rel="index" title="Index"
+ href="../../../genindex.html"/>
+ <link rel="search" title="Search" href="../../../search.html"/>
+ <link rel="top" title="Airflow Documentation" href="../../../index.html"/>
+ <link rel="up" title="Module code" href="../../index.html"/>
+
+
+ <script src="../../../_static/js/modernizr.min.js"></script>
+
+</head>
+
+<body class="wy-body-for-nav" role="document">
+
+
+ <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" role="navigation" 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.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"># "License"); 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"># "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span>
+<span class="c1"># KIND, either express or implied. See the License for the</span>
+<span class="c1"># specific language governing permissions and limitations</span>
+<span class="c1"># under the License.</span>
+
+<span class="kn">from</span> <span class="nn">builtins</span> <span class="k">import</span> <span class="nb">str</span>
+<span class="kn">import</span> <span class="nn">dill</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">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="p">,</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">textwrap</span> <span class="k">import</span> <span class="n">dedent</span>
+
+
+<div class="viewcode-block" id="PythonOperator"><a class="viewcode-back" href="../../../code.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">"""</span>
+<span class="sd"> Executes a Python callable</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</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</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'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 ``['.sql', '.hql']``</span>
+<span class="sd"> :type templates_exts: list(str)</span>
+<span class="sd"> """</span>
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'templates_dict'</span><span class="p">,)</span>
+ <span class="n">template_ext</span> <span class="o">=</span> <span class="nb">tuple</span><span class="p">()</span>
+ <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#ffefeb'</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">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">'`python_callable` param must be callable'</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>
+
+ <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="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">'templates_dict'</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">"Done. Returned value was: </span><span class="si">%s</span><span class="s2">"</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>
+
+ <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 class="viewcode-block" id="BranchPythonOperator"><a class="viewcode-back" href="../../../code.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">"""</span>
+<span class="sd"> Allows a workflow to "branch" or follow a single path following the</span>
+<span class="sd"> execution of this task.</span>
+
+<span class="sd"> It derives the PythonOperator and expects a Python function that returns</span>
+<span class="sd"> the task_id to follow. The task_id returned should point to a task</span>
+<span class="sd"> directly downstream from {self}. All other "branches" or</span>
+<span class="sd"> directly downstream tasks are marked with a state of ``skipped`` so that</span>
+<span class="sd"> these paths can't move forward. The ``skipped`` states are propageted</span>
+<span class="sd"> downstream to allow for the DAG state to fill up and the DAG run'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"> """</span>
+ <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="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">"Following branch </span><span class="si">%s</span><span class="s2">"</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">"Marking other directly downstream tasks as skipped"</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">'task'</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">"Downstream task_ids </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">downstream_tasks</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="o">!=</span> <span class="n">branch</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">'dag_run'</span><span class="p">],</span> <span class="n">context</span><span class="p">[</span><span class="s1">'ti'</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">"Done."</span><span class="p">)</span></div>
+
+
+<div class="viewcode-block" id="ShortCircuitOperator"><a class="viewcode-back" href="../../../code.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">"""</span>
+<span class="sd"> Allows a workflow to continue only if a condition is met. Otherwise, the</span>
+<span class="sd"> workflow "short-circuits" 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 "skipped". 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"> """</span>
+ <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">"Condition result is </span><span class="si">%s</span><span class="s2">"</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">'Proceeding with downstream tasks...'</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">'Skipping downstream tasks...'</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">'task'</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">"Downstream task_ids </span><span class="si">%s</span><span class="s2">"</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">'dag_run'</span><span class="p">],</span> <span class="n">context</span><span class="p">[</span><span class="s1">'ti'</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">"Done."</span><span class="p">)</span></div>
+
+<div class="viewcode-block" id="PythonVirtualenvOperator"><a class="viewcode-back" href="../../../code.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">"""</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 part of a class. All imports</span>
+<span class="sd"> must happen inside the function and no variables outside of the scope may be referenced.</span>
+<span class="sd"> A global scope 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 the args and result (pickle is default).</span>
+<span class="sd"> This allow more complex types 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 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 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'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 ``['.sql', '.hql']``</span>
+<span class="sd"> :type templates_exts: list(str)</span>
+<span class="sd"> """</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">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="kc">False</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">'dill'</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">'If using dill, dill must be in the environment '</span> <span class="o">+</span>
+ <span class="s1">'either via system_site_packages or requirements'</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="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">'</span><span class="si">{}</span><span class="s1"> only supports functions for python_callable arg'</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">"Passing op_args or op_kwargs is not supported across "</span>
+ <span class="s2">"different Python major versions "</span>
+ <span class="s2">"for PythonVirtualenvOperator. Please use string_args."</span><span class="p">)</span>
+
+ <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">'venv'</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">'templates_dict'</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">'script.in'</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">'script.out'</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">'string_args.txt'</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">'script.py'</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>
+
+ <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">></span> <span class="mi">0</span>
+
+ <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">"Executing cmd</span><span class="se">\n</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</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">"Got output</span><span class="se">\n</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</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">"Got error output</span><span class="se">\n</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</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>
+
+ <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">'w'</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">'</span><span class="se">\n</span><span class="s1">'</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>
+
+ <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">'wb'</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">'args'</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">'kwargs'</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>
+
+ <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">'rb'</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">"Error deserializing result. Note that result deserialization "</span>
+ <span class="s2">"is not supported across major Python versions."</span><span class="p">)</span>
+ <span class="k">raise</span>
+
+ <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">'w'</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">'Writing code to file</span><span class="se">\n</span><span class="si">{}</span><span class="s1">'</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>
+
+ <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">'virtualenv'</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">'--system-site-packages'</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">'--python=python</span><span class="si">{}</span><span class="s1">'</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>
+
+ <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">'</span><span class="si">{}</span><span class="s1">/bin/pip'</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">'install'</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>
+
+ <span class="k">def</span> <span class="nf">_generate_python_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">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">'</span><span class="si">{}</span><span class="s1">/bin/python'</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>
+
+ <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">'dill'</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="n">pickling_library</span> <span class="o">=</span> <span class="s1">'pickle'</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">'with open(sys.argv[1], "rb") as f: arg_dict = </span><span class="si">{}</span><span class="s1">.load(f)'</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">'arg_dict = {"args": [], "kwargs": </span><span class="si">{}</span><span class="s1">}'</span>
+
+ <span class="c1"># no indents in original code so we can accept 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">"""</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["args"]</span>
+<span class="s2"> kwargs = arg_dict["kwargs"]</span>
+<span class="s2"> with open(sys.argv[3], 'r') as f: 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], 'wb') as f: res is not None and </span><span class="si">{pickling_library}</span><span class="s2">.dump(res, f)</span>
+<span class="s2"> """</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">"Done."</span><span class="p">)</span></div>
+
+</pre></div>
+
+ </div>
+ <div class="articleComments">
+
+ </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/snide/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">
+ var DOCUMENTATION_OPTIONS = {
+ URL_ROOT:'../../../',
+ VERSION:'',
+ COLLAPSE_INDEX:false,
+ FILE_SUFFIX:'.html',
+ HAS_SOURCE: true,
+ SOURCELINK_SUFFIX: '.txt'
+ };
+ </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.StickyNav.enable();
+ });
+ </script>
+
+
+</body>
+</html>
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/11437c14/_modules/airflow/operators/redshift_to_s3_operator.html
----------------------------------------------------------------------
diff --git a/_modules/airflow/operators/redshift_to_s3_operator.html b/_modules/airflow/operators/redshift_to_s3_operator.html
index 6b8e248..a68f20e 100644
--- a/_modules/airflow/operators/redshift_to_s3_operator.html
+++ b/_modules/airflow/operators/redshift_to_s3_operator.html
@@ -91,7 +91,7 @@
<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="../../../configuration.html">Configuration</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>
@@ -99,8 +99,10 @@
<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>
@@ -169,17 +171,22 @@
<h1>Source code for airflow.operators.redshift_to_s3_operator</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="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"># "License"); 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"># "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span>
+<span class="c1"># KIND, either express or implied. See the License for the</span>
+<span class="c1"># specific language governing permissions and limitations</span>
+<span class="c1"># under the License.</span>
<span class="kn">from</span> <span class="nn">airflow.hooks.postgres_hook</span> <span class="k">import</span> <span class="n">PostgresHook</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>
@@ -189,6 +196,7 @@
<div class="viewcode-block" id="RedshiftToS3Transfer"><a class="viewcode-back" href="../../../integration.html#airflow.operators.redshift_to_s3_operator.RedshiftToS3Transfer">[docs]</a><span class="k">class</span> <span class="nc">RedshiftToS3Transfer</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Executes an UNLOAD command to s3 as a CSV with headers</span>
+
<span class="sd"> :param schema: reference to a specific schema in redshift database</span>
<span class="sd"> :type schema: string</span>
<span class="sd"> :param table: reference to a specific table in redshift database</span>
@@ -201,8 +209,8 @@
<span class="sd"> :type redshift_conn_id: string</span>
<span class="sd"> :param aws_conn_id: reference to a specific S3 connection</span>
<span class="sd"> :type aws_conn_id: string</span>
-<span class="sd"> :param options: reference to a list of UNLOAD options</span>
-<span class="sd"> :type options: list</span>
+<span class="sd"> :param unload_options: reference to a list of UNLOAD options</span>
+<span class="sd"> :type unload_options: list</span>
<span class="sd"> """</span>
<span class="n">template_fields</span> <span class="o">=</span> <span class="p">()</span>
@@ -221,6 +229,7 @@
<span class="n">unload_options</span><span class="o">=</span><span class="nb">tuple</span><span class="p">(),</span>
<span class="n">autocommit</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">parameters</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">include_header</span><span class="o">=</span><span class="kc">False</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">RedshiftToS3Transfer</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="bp">self</span><span class="o">.</span><span class="n">schema</span> <span class="o">=</span> <span class="n">schema</span>
@@ -232,41 +241,68 @@
<span class="bp">self</span><span class="o">.</span><span class="n">unload_options</span> <span class="o">=</span> <span class="n">unload_options</span>
<span class="bp">self</span><span class="o">.</span><span class="n">autocommit</span> <span class="o">=</span> <span class="n">autocommit</span>
<span class="bp">self</span><span class="o">.</span><span class="n">parameters</span> <span class="o">=</span> <span class="n">parameters</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">include_header</span> <span class="o">=</span> <span class="n">include_header</span>
+
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">include_header</span> <span class="ow">and</span> \
+ <span class="s1">'PARALLEL OFF'</span> <span class="ow">not</span> <span class="ow">in</span> <span class="p">[</span><span class="n">uo</span><span class="o">.</span><span class="n">upper</span><span class="p">()</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span> <span class="k">for</span> <span class="n">uo</span> <span class="ow">in</span> <span class="n">unload_options</span><span class="p">]:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">unload_options</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">unload_options</span><span class="p">)</span> <span class="o">+</span> <span class="p">[</span><span class="s1">'PARALLEL OFF'</span><span class="p">,</span> <span class="p">]</span>
<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="bp">self</span><span class="o">.</span><span class="n">hook</span> <span class="o">=</span> <span class="n">PostgresHook</span><span class="p">(</span><span class="n">postgres_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">redshift_conn_id</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">s3</span> <span class="o">=</span> <span class="n">S3Hook</span><span class="p">(</span><span class="n">aws_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">aws_conn_id</span><span class="p">)</span>
- <span class="n">a_key</span><span class="p">,</span> <span class="n">s_key</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">s3</span><span class="o">.</span><span class="n">get_credentials</span><span class="p">()</span>
+ <span class="n">credentials</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">s3</span><span class="o">.</span><span class="n">get_credentials</span><span class="p">()</span>
<span class="n">unload_options</span> <span class="o">=</span> <span class="s1">'</span><span class="se">\n\t\t\t</span><span class="s1">'</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">unload_options</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">"Retrieving headers from </span><span class="si">%s</span><span class="s2">.</span><span class="si">%s</span><span class="s2">..."</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">table</span><span class="p">)</span>
-
- <span class="n">columns_query</span> <span class="o">=</span> <span class="s2">"""SELECT column_name</span>
-<span class="s2"> FROM information_schema.columns</span>
-<span class="s2"> WHERE table_schema = '</span><span class="si">{0}</span><span class="s2">'</span>
-<span class="s2"> AND table_name = '</span><span class="si">{1}</span><span class="s2">'</span>
-<span class="s2"> ORDER BY ordinal_position</span>
-<span class="s2"> """</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">schema</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">table</span><span class="p">)</span>
-
- <span class="n">cursor</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">hook</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span><span class="o">.</span><span class="n">cursor</span><span class="p">()</span>
- <span class="n">cursor</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">columns_query</span><span class="p">)</span>
- <span class="n">rows</span> <span class="o">=</span> <span class="n">cursor</span><span class="o">.</span><span class="n">fetchall</span><span class="p">()</span>
- <span class="n">columns</span> <span class="o">=</span> <span class="nb">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">row</span><span class="p">:</span> <span class="n">row</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">rows</span><span class="p">)</span>
- <span class="n">column_names</span> <span class="o">=</span> <span class="s1">', '</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="k">lambda</span> <span class="n">c</span><span class="p">:</span> <span class="s2">"</span><span class="se">\\</span><span class="s2">'</span><span class="si">{0}</span><span class="se">\\</span><span class="s2">'"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">c</span><span class="p">),</span> <span class="n">columns</span><span class="p">))</span>
- <span class="n">column_castings</span> <span class="o">=</span> <span class="s1">', '</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="k">lambda</span> <span class="n">c</span><span class="p">:</span> <span class="s2">"CAST(</span><span class="si">{0}</span><span class="s2"> AS text) AS </span><span class="si">{0}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">c</span><span class="p">),</span>
- <span class="n">columns</span><span class="p">))</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">include_header</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">"Retrieving headers from </span><span class="si">%s</span><span class="s2">.</span><span class="si">%s</span><span class="s2">..."</span><span class="p">,</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">table</span><span class="p">)</span>
+
+ <span class="n">columns_query</span> <span class="o">=</span> <span class="s2">"""SELECT column_name</span>
+<span class="s2"> FROM information_schema.columns</span>
+<span class="s2"> WHERE table_schema = '</span><span class="si">{schema}</span><span class="s2">'</span>
+<span class="s2"> AND table_name = '</span><span class="si">{table}</span><span class="s2">'</span>
+<span class="s2"> ORDER BY ordinal_position</span>
+<span class="s2"> """</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">schema</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="p">,</span>
+ <span class="n">table</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">table</span><span class="p">)</span>
+
+ <span class="n">cursor</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">hook</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span><span class="o">.</span><span class="n">cursor</span><span class="p">()</span>
+ <span class="n">cursor</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">columns_query</span><span class="p">)</span>
+ <span class="n">rows</span> <span class="o">=</span> <span class="n">cursor</span><span class="o">.</span><span class="n">fetchall</span><span class="p">()</span>
+ <span class="n">columns</span> <span class="o">=</span> <span class="p">[</span><span class="n">row</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">row</span> <span class="ow">in</span> <span class="n">rows</span><span class="p">]</span>
+ <span class="n">column_names</span> <span class="o">=</span> <span class="s1">', '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="s2">"</span><span class="si">{0}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">c</span><span class="p">)</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">columns</span><span class="p">)</span>
+ <span class="n">column_headers</span> <span class="o">=</span> <span class="s1">', '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="s2">"</span><span class="se">\\</span><span class="s2">'</span><span class="si">{0}</span><span class="se">\\</span><span class="s2">'"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">c</span><span class="p">)</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">columns</span><span class="p">)</span>
+ <span class="n">column_castings</span> <span class="o">=</span> <span class="s1">', '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="s2">"CAST(</span><span class="si">{0}</span><span class="s2"> AS text) AS </span><span class="si">{0}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">c</span><span class="p">)</span>
+ <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">columns</span><span class="p">)</span>
+
+ <span class="n">select_query</span> <span class="o">=</span> <span class="s2">"""SELECT </span><span class="si">{column_names}</span><span class="s2"> FROM</span>
+<span class="s2"> (SELECT 2 sort_order, </span><span class="si">{column_castings}</span><span class="s2"></span>
+<span class="s2"> FROM </span><span class="si">{schema}</span><span class="s2">.</span><span class="si">{table}</span><span class="s2"></span>
+<span class="s2"> UNION ALL</span>
+<span class="s2"> SELECT 1 sort_order, </span><span class="si">{column_headers}</span><span class="s2">)</span>
+<span class="s2"> ORDER BY sort_order"""</span>\
+ <span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">column_names</span><span class="o">=</span><span class="n">column_names</span><span class="p">,</span>
+ <span class="n">column_castings</span><span class="o">=</span><span class="n">column_castings</span><span class="p">,</span>
+ <span class="n">column_headers</span><span class="o">=</span><span class="n">column_headers</span><span class="p">,</span>
+ <span class="n">schema</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="p">,</span>
+ <span class="n">table</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">table</span><span class="p">)</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="n">select_query</span> <span class="o">=</span> <span class="s2">"SELECT * FROM </span><span class="si">{schema}</span><span class="s2">.</span><span class="si">{table}</span><span class="s2">"</span>\
+ <span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">schema</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="p">,</span>
+ <span class="n">table</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">table</span><span class="p">)</span>
<span class="n">unload_query</span> <span class="o">=</span> <span class="s2">"""</span>
-<span class="s2"> UNLOAD ('SELECT </span><span class="si">{0}</span><span class="s2"></span>
-<span class="s2"> UNION ALL</span>
-<span class="s2"> SELECT </span><span class="si">{1}</span><span class="s2"> FROM </span><span class="si">{2}</span><span class="s2">.</span><span class="si">{3}</span><span class="s2"></span>
-<span class="s2"> ORDER BY 1 DESC')</span>
-<span class="s2"> TO 's3://</span><span class="si">{4}</span><span class="s2">/</span><span class="si">{5}</span><span class="s2">/</span><span class="si">{3}</span><span class="s2">_'</span>
-<span class="s2"> with</span>
-<span class="s2"> credentials 'aws_access_key_id=</span><span class="si">{6}</span><span class="s2">;aws_secret_access_key=</span><span class="si">{7}</span><span class="s2">'</span>
-<span class="s2"> </span><span class="si">{8}</span><span class="s2">;</span>
-<span class="s2"> """</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">column_names</span><span class="p">,</span> <span class="n">column_castings</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">table</span><span class="p">,</span>
- <span class="bp">self</span><span class="o">.</span><span class="n">s3_bucket</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">s3_key</span><span class="p">,</span> <span class="n">a_key</span><span class="p">,</span> <span class="n">s_key</span><span class="p">,</span> <span class="n">unload_options</span><span class="p">)</span>
+<span class="s2"> UNLOAD ('</span><span class="si">{select_query}</span><span class="s2">')</span>
+<span class="s2"> TO 's3://</span><span class="si">{s3_bucket}</span><span class="s2">/</span><span class="si">{s3_key}</span><span class="s2">/</span><span class="si">{table}</span><span class="s2">_'</span>
+<span class="s2"> with credentials</span>
+<span class="s2"> 'aws_access_key_id=</span><span class="si">{access_key}</span><span class="s2">;aws_secret_access_key=</span><span class="si">{secret_key}</span><span class="s2">'</span>
+<span class="s2"> </span><span class="si">{unload_options}</span><span class="s2">;</span>
+<span class="s2"> """</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">select_query</span><span class="o">=</span><span class="n">select_query</span><span class="p">,</span>
+ <span class="n">table</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">table</span><span class="p">,</span>
+ <span class="n">s3_bucket</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">s3_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">access_key</span><span class="o">=</span><span class="n">credentials</span><span class="o">.</span><span class="n">access_key</span><span class="p">,</span>
+ <span class="n">secret_key</span><span class="o">=</span><span class="n">credentials</span><span class="o">.</span><span class="n">secret_key</span><span class="p">,</span>
+ <span class="n">unload_options</span><span class="o">=</span><span class="n">unload_options</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">'Executing UNLOAD command...'</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hook</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">unload_query</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">autocommit</span><span class="p">)</span>