blob: 7edeae9da1a5daf23e41a4121ed2685db914d0ce [file] [log] [blame]
<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>airflow.contrib.hooks.gcp_dataproc_hook &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="../hooks.html">airflow.contrib.hooks</a> &raquo;</li>
<li>airflow.contrib.hooks.gcp_dataproc_hook</li>
<li class="wy-breadcrumbs-aside">
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<h1>Source code for airflow.contrib.hooks.gcp_dataproc_hook</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="c1">#</span>
<span class="kn">import</span> <span class="nn">time</span>
<span class="kn">import</span> <span class="nn">uuid</span>
<span class="kn">from</span> <span class="nn">googleapiclient.discovery</span> <span class="k">import</span> <span class="n">build</span>
<span class="kn">from</span> <span class="nn">zope.deprecation</span> <span class="k">import</span> <span class="n">deprecation</span>
<span class="kn">from</span> <span class="nn">airflow.contrib.hooks.gcp_api_base_hook</span> <span class="k">import</span> <span class="n">GoogleCloudBaseHook</span>
<span class="kn">from</span> <span class="nn">airflow.utils.log.logging_mixin</span> <span class="k">import</span> <span class="n">LoggingMixin</span>
<div class="viewcode-block" id="_DataProcJob"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJob">[docs]</a><span class="k">class</span> <span class="nc">_DataProcJob</span><span class="p">(</span><span class="n">LoggingMixin</span><span class="p">):</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">dataproc_api</span><span class="p">,</span> <span class="n">project_id</span><span class="p">,</span> <span class="n">job</span><span class="p">,</span> <span class="n">region</span><span class="o">=</span><span class="s1">&#39;global&#39;</span><span class="p">,</span>
<span class="n">job_error_states</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dataproc_api</span> <span class="o">=</span> <span class="n">dataproc_api</span>
<span class="bp">self</span><span class="o">.</span><span class="n">project_id</span> <span class="o">=</span> <span class="n">project_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">region</span> <span class="o">=</span> <span class="n">region</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job</span> <span class="o">=</span> <span class="n">dataproc_api</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">regions</span><span class="p">()</span><span class="o">.</span><span class="n">jobs</span><span class="p">()</span><span class="o">.</span><span class="n">submit</span><span class="p">(</span>
<span class="n">projectId</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">project_id</span><span class="p">,</span>
<span class="n">region</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">region</span><span class="p">,</span>
<span class="n">body</span><span class="o">=</span><span class="n">job</span><span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job_id</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s1">&#39;reference&#39;</span><span class="p">][</span><span class="s1">&#39;jobId&#39;</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job_error_states</span> <span class="o">=</span> <span class="n">job_error_states</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;DataProc job </span><span class="si">%s</span><span class="s1"> is </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job_id</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">job</span><span class="p">[</span><span class="s1">&#39;status&#39;</span><span class="p">][</span><span class="s1">&#39;state&#39;</span><span class="p">])</span>
<span class="p">)</span>
<div class="viewcode-block" id="_DataProcJob.wait_for_done"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJob.wait_for_done">[docs]</a> <span class="k">def</span> <span class="nf">wait_for_done</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">while</span> <span class="kc">True</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_api</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">regions</span><span class="p">()</span><span class="o">.</span><span class="n">jobs</span><span class="p">()</span><span class="o">.</span><span class="n">get</span><span class="p">(</span>
<span class="n">projectId</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">project_id</span><span class="p">,</span>
<span class="n">region</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">region</span><span class="p">,</span>
<span class="n">jobId</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">job_id</span><span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">num_retries</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span>
<span class="k">if</span> <span class="s1">&#39;ERROR&#39;</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s1">&#39;status&#39;</span><span class="p">][</span><span class="s1">&#39;state&#39;</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="s1">&#39;DataProc job </span><span class="si">%s</span><span class="s1"> has errors&#39;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">job_id</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="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s1">&#39;status&#39;</span><span class="p">][</span><span class="s1">&#39;details&#39;</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="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">))</span>
<span class="k">return</span> <span class="kc">False</span>
<span class="k">if</span> <span class="s1">&#39;CANCELLED&#39;</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s1">&#39;status&#39;</span><span class="p">][</span><span class="s1">&#39;state&#39;</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">warning</span><span class="p">(</span><span class="s1">&#39;DataProc job </span><span class="si">%s</span><span class="s1"> is cancelled&#39;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">job_id</span><span class="p">)</span>
<span class="k">if</span> <span class="s1">&#39;details&#39;</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s1">&#39;status&#39;</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">warning</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s1">&#39;status&#39;</span><span class="p">][</span><span class="s1">&#39;details&#39;</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="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">))</span>
<span class="k">return</span> <span class="kc">False</span>
<span class="k">if</span> <span class="s1">&#39;DONE&#39;</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s1">&#39;status&#39;</span><span class="p">][</span><span class="s1">&#39;state&#39;</span><span class="p">]:</span>
<span class="k">return</span> <span class="kc">True</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;DataProc job </span><span class="si">%s</span><span class="s1"> is </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job_id</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">job</span><span class="p">[</span><span class="s1">&#39;status&#39;</span><span class="p">][</span><span class="s1">&#39;state&#39;</span><span class="p">])</span>
<span class="p">)</span>
<span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="mi">5</span><span class="p">)</span></div>
<div class="viewcode-block" id="_DataProcJob.raise_error"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJob.raise_error">[docs]</a> <span class="k">def</span> <span class="nf">raise_error</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">message</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="n">job_state</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s1">&#39;status&#39;</span><span class="p">][</span><span class="s1">&#39;state&#39;</span><span class="p">]</span>
<span class="c1"># We always consider ERROR to be an error state.</span>
<span class="k">if</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">job_error_states</span> <span class="ow">and</span> <span class="n">job_state</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">job_error_states</span><span class="p">)</span> <span class="ow">or</span> <span class="s1">&#39;ERROR&#39;</span> <span class="o">==</span> <span class="n">job_state</span><span class="p">:</span>
<span class="n">ex_message</span> <span class="o">=</span> <span class="n">message</span> <span class="ow">or</span> <span class="p">(</span><span class="s2">&quot;Google DataProc job has state: </span><span class="si">%s</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">job_state</span><span class="p">)</span>
<span class="n">ex_details</span> <span class="o">=</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">job</span><span class="p">[</span><span class="s1">&#39;status&#39;</span><span class="p">][</span><span class="s1">&#39;details&#39;</span><span class="p">])</span>
<span class="k">if</span> <span class="s1">&#39;details&#39;</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s1">&#39;status&#39;</span><span class="p">]</span>
<span class="k">else</span> <span class="s2">&quot;No details available&quot;</span><span class="p">)</span>
<span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span><span class="n">ex_message</span> <span class="o">+</span> <span class="s2">&quot;: &quot;</span> <span class="o">+</span> <span class="n">ex_details</span><span class="p">)</span></div>
<div class="viewcode-block" id="_DataProcJob.get"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJob.get">[docs]</a> <span class="k">def</span> <span class="nf">get</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">job</span></div></div>
<div class="viewcode-block" id="_DataProcJobBuilder"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder">[docs]</a><span class="k">class</span> <span class="nc">_DataProcJobBuilder</span><span class="p">:</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">project_id</span><span class="p">,</span> <span class="n">task_id</span><span class="p">,</span> <span class="n">cluster_name</span><span class="p">,</span> <span class="n">job_type</span><span class="p">,</span> <span class="n">properties</span><span class="p">):</span>
<span class="n">name</span> <span class="o">=</span> <span class="n">task_id</span> <span class="o">+</span> <span class="s2">&quot;_&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">uuid</span><span class="o">.</span><span class="n">uuid4</span><span class="p">())[:</span><span class="mi">8</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job_type</span> <span class="o">=</span> <span class="n">job_type</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;job&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;reference&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;projectId&quot;</span><span class="p">:</span> <span class="n">project_id</span><span class="p">,</span>
<span class="s2">&quot;jobId&quot;</span><span class="p">:</span> <span class="n">name</span><span class="p">,</span>
<span class="p">},</span>
<span class="s2">&quot;placement&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;clusterName&quot;</span><span class="p">:</span> <span class="n">cluster_name</span>
<span class="p">},</span>
<span class="n">job_type</span><span class="p">:</span> <span class="p">{</span>
<span class="p">}</span>
<span class="p">}</span>
<span class="p">}</span>
<span class="k">if</span> <span class="n">properties</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s2">&quot;job&quot;</span><span class="p">][</span><span class="n">job_type</span><span class="p">][</span><span class="s2">&quot;properties&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">properties</span>
<div class="viewcode-block" id="_DataProcJobBuilder.add_variables"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.add_variables">[docs]</a> <span class="k">def</span> <span class="nf">add_variables</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">variables</span><span class="p">):</span>
<span class="k">if</span> <span class="n">variables</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s2">&quot;job&quot;</span><span class="p">][</span><span class="bp">self</span><span class="o">.</span><span class="n">job_type</span><span class="p">][</span><span class="s2">&quot;scriptVariables&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">variables</span></div>
<div class="viewcode-block" id="_DataProcJobBuilder.add_args"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.add_args">[docs]</a> <span class="k">def</span> <span class="nf">add_args</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">args</span><span class="p">):</span>
<span class="k">if</span> <span class="n">args</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s2">&quot;job&quot;</span><span class="p">][</span><span class="bp">self</span><span class="o">.</span><span class="n">job_type</span><span class="p">][</span><span class="s2">&quot;args&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">args</span></div>
<div class="viewcode-block" id="_DataProcJobBuilder.add_query"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.add_query">[docs]</a> <span class="k">def</span> <span class="nf">add_query</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s2">&quot;job&quot;</span><span class="p">][</span><span class="bp">self</span><span class="o">.</span><span class="n">job_type</span><span class="p">][</span><span class="s2">&quot;queryList&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;queries&#39;</span><span class="p">:</span> <span class="p">[</span><span class="n">query</span><span class="p">]}</span></div>
<div class="viewcode-block" id="_DataProcJobBuilder.add_query_uri"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.add_query_uri">[docs]</a> <span class="k">def</span> <span class="nf">add_query_uri</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query_uri</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s2">&quot;job&quot;</span><span class="p">][</span><span class="bp">self</span><span class="o">.</span><span class="n">job_type</span><span class="p">][</span><span class="s2">&quot;queryFileUri&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">query_uri</span></div>
<div class="viewcode-block" id="_DataProcJobBuilder.add_jar_file_uris"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.add_jar_file_uris">[docs]</a> <span class="k">def</span> <span class="nf">add_jar_file_uris</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">jars</span><span class="p">):</span>
<span class="k">if</span> <span class="n">jars</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s2">&quot;job&quot;</span><span class="p">][</span><span class="bp">self</span><span class="o">.</span><span class="n">job_type</span><span class="p">][</span><span class="s2">&quot;jarFileUris&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">jars</span></div>
<div class="viewcode-block" id="_DataProcJobBuilder.add_archive_uris"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.add_archive_uris">[docs]</a> <span class="k">def</span> <span class="nf">add_archive_uris</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">archives</span><span class="p">):</span>
<span class="k">if</span> <span class="n">archives</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s2">&quot;job&quot;</span><span class="p">][</span><span class="bp">self</span><span class="o">.</span><span class="n">job_type</span><span class="p">][</span><span class="s2">&quot;archiveUris&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">archives</span></div>
<div class="viewcode-block" id="_DataProcJobBuilder.add_file_uris"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.add_file_uris">[docs]</a> <span class="k">def</span> <span class="nf">add_file_uris</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">files</span><span class="p">):</span>
<span class="k">if</span> <span class="n">files</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s2">&quot;job&quot;</span><span class="p">][</span><span class="bp">self</span><span class="o">.</span><span class="n">job_type</span><span class="p">][</span><span class="s2">&quot;fileUris&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">files</span></div>
<div class="viewcode-block" id="_DataProcJobBuilder.add_python_file_uris"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.add_python_file_uris">[docs]</a> <span class="k">def</span> <span class="nf">add_python_file_uris</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pyfiles</span><span class="p">):</span>
<span class="k">if</span> <span class="n">pyfiles</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s2">&quot;job&quot;</span><span class="p">][</span><span class="bp">self</span><span class="o">.</span><span class="n">job_type</span><span class="p">][</span><span class="s2">&quot;pythonFileUris&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">pyfiles</span></div>
<div class="viewcode-block" id="_DataProcJobBuilder.set_main"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.set_main">[docs]</a> <span class="k">def</span> <span class="nf">set_main</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">main_jar</span><span class="p">,</span> <span class="n">main_class</span><span class="p">):</span>
<span class="k">if</span> <span class="n">main_class</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">main_jar</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span><span class="s2">&quot;Set either main_jar or main_class&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">main_jar</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s2">&quot;job&quot;</span><span class="p">][</span><span class="bp">self</span><span class="o">.</span><span class="n">job_type</span><span class="p">][</span><span class="s2">&quot;mainJarFileUri&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">main_jar</span>
<span class="k">else</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s2">&quot;job&quot;</span><span class="p">][</span><span class="bp">self</span><span class="o">.</span><span class="n">job_type</span><span class="p">][</span><span class="s2">&quot;mainClass&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">main_class</span></div>
<div class="viewcode-block" id="_DataProcJobBuilder.set_python_main"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.set_python_main">[docs]</a> <span class="k">def</span> <span class="nf">set_python_main</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">main</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s2">&quot;job&quot;</span><span class="p">][</span><span class="bp">self</span><span class="o">.</span><span class="n">job_type</span><span class="p">][</span><span class="s2">&quot;mainPythonFileUri&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">main</span></div>
<div class="viewcode-block" id="_DataProcJobBuilder.set_job_name"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.set_job_name">[docs]</a> <span class="k">def</span> <span class="nf">set_job_name</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s2">&quot;job&quot;</span><span class="p">][</span><span class="s2">&quot;reference&quot;</span><span class="p">][</span><span class="s2">&quot;jobId&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">name</span> <span class="o">+</span> <span class="s2">&quot;_&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">uuid</span><span class="o">.</span><span class="n">uuid4</span><span class="p">())[:</span><span class="mi">8</span><span class="p">]</span></div>
<div class="viewcode-block" id="_DataProcJobBuilder.build"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.build">[docs]</a> <span class="k">def</span> <span class="nf">build</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">job</span></div></div>
<div class="viewcode-block" id="_DataProcOperation"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcOperation">[docs]</a><span class="k">class</span> <span class="nc">_DataProcOperation</span><span class="p">(</span><span class="n">LoggingMixin</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Continuously polls Dataproc Operation until it completes.&quot;&quot;&quot;</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">dataproc_api</span><span class="p">,</span> <span class="n">operation</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dataproc_api</span> <span class="o">=</span> <span class="n">dataproc_api</span>
<span class="bp">self</span><span class="o">.</span><span class="n">operation</span> <span class="o">=</span> <span class="n">operation</span>
<span class="bp">self</span><span class="o">.</span><span class="n">operation_name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">operation</span><span class="p">[</span><span class="s1">&#39;name&#39;</span><span class="p">]</span>
<div class="viewcode-block" id="_DataProcOperation.wait_for_done"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcOperation.wait_for_done">[docs]</a> <span class="k">def</span> <span class="nf">wait_for_done</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">_check_done</span><span class="p">():</span>
<span class="k">return</span> <span class="kc">True</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;Waiting for Dataproc Operation </span><span class="si">%s</span><span class="s1"> to finish&#39;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">operation_name</span><span class="p">)</span>
<span class="k">while</span> <span class="kc">True</span><span class="p">:</span>
<span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="mi">10</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">operation</span> <span class="o">=</span> <span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dataproc_api</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span>
<span class="o">.</span><span class="n">regions</span><span class="p">()</span>
<span class="o">.</span><span class="n">operations</span><span class="p">()</span>
<span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">operation_name</span><span class="p">)</span>
<span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">num_retries</span><span class="o">=</span><span class="mi">5</span><span class="p">))</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_check_done</span><span class="p">():</span>
<span class="k">return</span> <span class="kc">True</span></div>
<div class="viewcode-block" id="_DataProcOperation.get"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcOperation.get">[docs]</a> <span class="k">def</span> <span class="nf">get</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">operation</span></div>
<div class="viewcode-block" id="_DataProcOperation._check_done"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcOperation._check_done">[docs]</a> <span class="k">def</span> <span class="nf">_check_done</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">if</span> <span class="s1">&#39;done&#39;</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">operation</span><span class="p">:</span>
<span class="k">if</span> <span class="s1">&#39;error&#39;</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">operation</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">warning</span><span class="p">(</span>
<span class="s1">&#39;Dataproc Operation </span><span class="si">%s</span><span class="s1"> failed with error: </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">operation_name</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">operation</span><span class="p">[</span><span class="s1">&#39;error&#39;</span><span class="p">][</span><span class="s1">&#39;message&#39;</span><span class="p">])</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_raise_error</span><span class="p">()</span>
<span class="k">else</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;Dataproc Operation </span><span class="si">%s</span><span class="s1"> done&#39;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">operation</span><span class="p">[</span><span class="s1">&#39;name&#39;</span><span class="p">])</span>
<span class="k">return</span> <span class="kc">True</span>
<span class="k">return</span> <span class="kc">False</span></div>
<div class="viewcode-block" id="_DataProcOperation._raise_error"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcOperation._raise_error">[docs]</a> <span class="k">def</span> <span class="nf">_raise_error</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span><span class="s1">&#39;Google Dataproc Operation </span><span class="si">%s</span><span class="s1"> failed: </span><span class="si">%s</span><span class="s1">&#39;</span> <span class="o">%</span>
<span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">operation_name</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">operation</span><span class="p">[</span><span class="s1">&#39;error&#39;</span><span class="p">][</span><span class="s1">&#39;message&#39;</span><span class="p">]))</span></div></div>
<div class="viewcode-block" id="DataProcHook"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook.DataProcHook">[docs]</a><span class="k">class</span> <span class="nc">DataProcHook</span><span class="p">(</span><span class="n">GoogleCloudBaseHook</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Hook for Google Cloud Dataproc APIs.&quot;&quot;&quot;</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">gcp_conn_id</span><span class="o">=</span><span class="s1">&#39;google_cloud_default&#39;</span><span class="p">,</span>
<span class="n">delegate_to</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">api_version</span><span class="o">=</span><span class="s1">&#39;v1beta2&#39;</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">DataProcHook</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">gcp_conn_id</span><span class="p">,</span> <span class="n">delegate_to</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">api_version</span> <span class="o">=</span> <span class="n">api_version</span>
<div class="viewcode-block" id="DataProcHook.get_conn"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook.DataProcHook.get_conn">[docs]</a> <span class="k">def</span> <span class="nf">get_conn</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Returns a Google Cloud Dataproc service object.&quot;&quot;&quot;</span>
<span class="n">http_authorized</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_authorize</span><span class="p">()</span>
<span class="k">return</span> <span class="n">build</span><span class="p">(</span>
<span class="s1">&#39;dataproc&#39;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">api_version</span><span class="p">,</span> <span class="n">http</span><span class="o">=</span><span class="n">http_authorized</span><span class="p">,</span>
<span class="n">cache_discovery</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span></div>
<div class="viewcode-block" id="DataProcHook.get_cluster"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook.DataProcHook.get_cluster">[docs]</a> <span class="k">def</span> <span class="nf">get_cluster</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">project_id</span><span class="p">,</span> <span class="n">region</span><span class="p">,</span> <span class="n">cluster_name</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">regions</span><span class="p">()</span><span class="o">.</span><span class="n">clusters</span><span class="p">()</span><span class="o">.</span><span class="n">get</span><span class="p">(</span>
<span class="n">projectId</span><span class="o">=</span><span class="n">project_id</span><span class="p">,</span>
<span class="n">region</span><span class="o">=</span><span class="n">region</span><span class="p">,</span>
<span class="n">clusterName</span><span class="o">=</span><span class="n">cluster_name</span>
<span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">num_retries</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span></div>
<div class="viewcode-block" id="DataProcHook.submit"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook.DataProcHook.submit">[docs]</a> <span class="k">def</span> <span class="nf">submit</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">project_id</span><span class="p">,</span> <span class="n">job</span><span class="p">,</span> <span class="n">region</span><span class="o">=</span><span class="s1">&#39;global&#39;</span><span class="p">,</span> <span class="n">job_error_states</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="n">submitted</span> <span class="o">=</span> <span class="n">_DataProcJob</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">(),</span> <span class="n">project_id</span><span class="p">,</span> <span class="n">job</span><span class="p">,</span> <span class="n">region</span><span class="p">,</span>
<span class="n">job_error_states</span><span class="o">=</span><span class="n">job_error_states</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">submitted</span><span class="o">.</span><span class="n">wait_for_done</span><span class="p">():</span>
<span class="n">submitted</span><span class="o">.</span><span class="n">raise_error</span><span class="p">()</span></div>
<div class="viewcode-block" id="DataProcHook.create_job_template"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook.DataProcHook.create_job_template">[docs]</a> <span class="k">def</span> <span class="nf">create_job_template</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">task_id</span><span class="p">,</span> <span class="n">cluster_name</span><span class="p">,</span> <span class="n">job_type</span><span class="p">,</span> <span class="n">properties</span><span class="p">):</span>
<span class="k">return</span> <span class="n">_DataProcJobBuilder</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">project_id</span><span class="p">,</span> <span class="n">task_id</span><span class="p">,</span> <span class="n">cluster_name</span><span class="p">,</span>
<span class="n">job_type</span><span class="p">,</span> <span class="n">properties</span><span class="p">)</span></div>
<div class="viewcode-block" id="DataProcHook.wait"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook.DataProcHook.wait">[docs]</a> <span class="k">def</span> <span class="nf">wait</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">operation</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Awaits for Google Cloud Dataproc Operation to complete.&quot;&quot;&quot;</span>
<span class="n">submitted</span> <span class="o">=</span> <span class="n">_DataProcOperation</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">(),</span> <span class="n">operation</span><span class="p">)</span>
<span class="n">submitted</span><span class="o">.</span><span class="n">wait_for_done</span><span class="p">()</span></div></div>
<span class="nb">setattr</span><span class="p">(</span>
<span class="n">DataProcHook</span><span class="p">,</span>
<span class="s2">&quot;await&quot;</span><span class="p">,</span>
<span class="n">deprecation</span><span class="o">.</span><span class="n">deprecated</span><span class="p">(</span>
<span class="n">DataProcHook</span><span class="o">.</span><span class="n">wait</span><span class="p">,</span> <span class="s2">&quot;renamed to &#39;wait&#39; for Python3.7 compatibility&quot;</span>
<span class="p">),</span>
<span class="p">)</span>
</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>