blob: 79a7288bb579e5820c7fe751c52905b3368da588 [file] [log] [blame]
<!--
Javascript to render AIRFLOW-XXX and PR references in text
as HTML links.
Overrides extrahead block from sphinx_rtd_theme
https://www.sphinx-doc.org/en/master/templating.html
-->
<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>airflow.contrib.hooks.gcp_dataflow_hook &mdash; Airflow Documentation</title>
<link rel="shortcut icon" href="../../../../_static/pin_32.png"/>
<script type="text/javascript" src="../../../../_static/js/modernizr.min.js"></script>
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/graphviz.css" type="text/css" />
<link rel="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>
<script type="text/javascript">
var _gaq = _gaq || [];
_gaq.push(['_setAccount', 'UA-140539454-1']);
_gaq.push(['_trackPageview']);
</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">
1.10.6
</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 Reference</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">REST API Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../integration.html">Integration</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../metrics.html">Metrics</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../errors.html">Error Tracking</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../kubernetes.html">Kubernetes</a></li>
<li class="toctree-l1"><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">Python API Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../privacy_notice.html">Privacy Notice</a></li>
</ul>
<p class="caption"><span class="caption-text">References</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../../_api/index.html">Python API</a></li>
</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_dataflow_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_dataflow_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="kn">import</span> <span class="nn">json</span>
<span class="kn">import</span> <span class="nn">re</span>
<span class="kn">import</span> <span class="nn">select</span>
<span class="kn">import</span> <span class="nn">subprocess</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">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>
<span class="c1"># This is the default location</span>
<span class="c1"># https://cloud.google.com/dataflow/pipelines/specifying-exec-params</span>
<div class="viewcode-block" id="DEFAULT_DATAFLOW_LOCATION"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataflow_hook/index.html#airflow.contrib.hooks.gcp_dataflow_hook.DEFAULT_DATAFLOW_LOCATION">[docs]</a><span class="n">DEFAULT_DATAFLOW_LOCATION</span> <span class="o">=</span> <span class="s1">&#39;us-central1&#39;</span></div>
<div class="viewcode-block" id="_DataflowJob"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataflow_hook/index.html#airflow.contrib.hooks.gcp_dataflow_hook._DataflowJob">[docs]</a><span class="k">class</span> <span class="nc">_DataflowJob</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">dataflow</span><span class="p">,</span> <span class="n">project_number</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">location</span><span class="p">,</span> <span class="n">poll_sleep</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span>
<span class="n">job_id</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">num_retries</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">_dataflow</span> <span class="o">=</span> <span class="n">dataflow</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_project_number</span> <span class="o">=</span> <span class="n">project_number</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_job_name</span> <span class="o">=</span> <span class="n">name</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_job_location</span> <span class="o">=</span> <span class="n">location</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_job_id</span> <span class="o">=</span> <span class="n">job_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_num_retries</span> <span class="o">=</span> <span class="n">num_retries</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">_get_job</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_poll_sleep</span> <span class="o">=</span> <span class="n">poll_sleep</span>
<div class="viewcode-block" id="_DataflowJob._get_job_id_from_name"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataflow_hook/index.html#airflow.contrib.hooks.gcp_dataflow_hook._DataflowJob._get_job_id_from_name">[docs]</a> <span class="k">def</span> <span class="nf">_get_job_id_from_name</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">jobs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dataflow</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">locations</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">list</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_number</span><span class="p">,</span>
<span class="n">location</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_job_location</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="bp">self</span><span class="o">.</span><span class="n">_num_retries</span><span class="p">)</span>
<span class="k">for</span> <span class="n">job</span> <span class="ow">in</span> <span class="n">jobs</span><span class="p">[</span><span class="s1">&#39;jobs&#39;</span><span class="p">]:</span>
<span class="k">if</span> <span class="n">job</span><span class="p">[</span><span class="s1">&#39;name&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job_name</span><span class="o">.</span><span class="n">lower</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="n">job</span><span class="p">[</span><span class="s1">&#39;id&#39;</span><span class="p">]</span>
<span class="k">return</span> <span class="n">job</span>
<span class="k">return</span> <span class="kc">None</span></div>
<div class="viewcode-block" id="_DataflowJob._get_job"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataflow_hook/index.html#airflow.contrib.hooks.gcp_dataflow_hook._DataflowJob._get_job">[docs]</a> <span class="k">def</span> <span class="nf">_get_job</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">_job_id</span><span class="p">:</span>
<span class="n">job</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dataflow</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">locations</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_number</span><span class="p">,</span>
<span class="n">location</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_job_location</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="bp">self</span><span class="o">.</span><span class="n">_num_retries</span><span class="p">)</span>
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job_name</span><span class="p">:</span>
<span class="n">job</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_job_id_from_name</span><span class="p">()</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span><span class="s1">&#39;Missing both dataflow job ID and name.&#39;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">job</span> <span class="ow">and</span> <span class="s1">&#39;currentState&#39;</span> <span class="ow">in</span> <span class="n">job</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;Google Cloud DataFlow 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="n">job</span><span class="p">[</span><span class="s1">&#39;name&#39;</span><span class="p">],</span> <span class="n">job</span><span class="p">[</span><span class="s1">&#39;currentState&#39;</span><span class="p">]</span>
<span class="p">)</span>
<span class="k">elif</span> <span class="n">job</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;Google Cloud DataFlow with job_id </span><span class="si">%s</span><span class="s1"> has name </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="n">job</span><span class="p">[</span><span class="s1">&#39;name&#39;</span><span class="p">]</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;Google Cloud DataFlow job not available yet..&#39;</span>
<span class="p">)</span>
<span class="k">return</span> <span class="n">job</span></div>
<div class="viewcode-block" id="_DataflowJob.wait_for_done"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataflow_hook/index.html#airflow.contrib.hooks.gcp_dataflow_hook._DataflowJob.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="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job</span> <span class="ow">and</span> <span class="s1">&#39;currentState&#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="k">if</span> <span class="s1">&#39;JOB_STATE_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;currentState&#39;</span><span class="p">]:</span>
<span class="k">return</span> <span class="kc">True</span>
<span class="k">elif</span> <span class="s1">&#39;JOB_STATE_RUNNING&#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;currentState&#39;</span><span class="p">]</span> <span class="ow">and</span> \
<span class="s1">&#39;JOB_TYPE_STREAMING&#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;type&#39;</span><span class="p">]:</span>
<span class="k">return</span> <span class="kc">True</span>
<span class="k">elif</span> <span class="s1">&#39;JOB_STATE_FAILED&#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;currentState&#39;</span><span class="p">]:</span>
<span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span><span class="s2">&quot;Google Cloud Dataflow job </span><span class="si">{}</span><span class="s2"> has failed.&quot;</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">_job</span><span class="p">[</span><span class="s1">&#39;name&#39;</span><span class="p">]))</span>
<span class="k">elif</span> <span class="s1">&#39;JOB_STATE_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;currentState&#39;</span><span class="p">]:</span>
<span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span><span class="s2">&quot;Google Cloud Dataflow job </span><span class="si">{}</span><span class="s2"> was cancelled.&quot;</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">_job</span><span class="p">[</span><span class="s1">&#39;name&#39;</span><span class="p">]))</span>
<span class="k">elif</span> <span class="s1">&#39;JOB_STATE_RUNNING&#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;currentState&#39;</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="bp">self</span><span class="o">.</span><span class="n">_poll_sleep</span><span class="p">)</span>
<span class="k">elif</span> <span class="s1">&#39;JOB_STATE_PENDING&#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;currentState&#39;</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">15</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">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">raise</span> <span class="ne">Exception</span><span class="p">(</span>
<span class="s2">&quot;Google Cloud Dataflow job </span><span class="si">{}</span><span class="s2"> was unknown state: </span><span class="si">{}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_job</span><span class="p">[</span><span class="s1">&#39;name&#39;</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;currentState&#39;</span><span class="p">]))</span>
<span class="k">else</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">15</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">_get_job</span><span class="p">()</span></div>
<div class="viewcode-block" id="_DataflowJob.get"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataflow_hook/index.html#airflow.contrib.hooks.gcp_dataflow_hook._DataflowJob.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="_Dataflow"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataflow_hook/index.html#airflow.contrib.hooks.gcp_dataflow_hook._Dataflow">[docs]</a><span class="k">class</span> <span class="nc">_Dataflow</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">cmd</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;Running command: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="s1">&#39; &#39;</span><span class="o">.</span><span class="n">join</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">_proc</span> <span class="o">=</span> <span class="n">subprocess</span><span class="o">.</span><span class="n">Popen</span><span class="p">(</span>
<span class="n">cmd</span><span class="p">,</span>
<span class="n">shell</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">stdout</span><span class="o">=</span><span class="n">subprocess</span><span class="o">.</span><span class="n">PIPE</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">PIPE</span><span class="p">,</span>
<span class="n">close_fds</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<div class="viewcode-block" id="_Dataflow._line"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataflow_hook/index.html#airflow.contrib.hooks.gcp_dataflow_hook._Dataflow._line">[docs]</a> <span class="k">def</span> <span class="nf">_line</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">fd</span><span class="p">):</span>
<span class="k">if</span> <span class="n">fd</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">stderr</span><span class="o">.</span><span class="n">fileno</span><span class="p">():</span>
<span class="n">line</span> <span class="o">=</span> <span class="sa">b</span><span class="s1">&#39;&#39;</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">_proc</span><span class="o">.</span><span class="n">stderr</span><span class="o">.</span><span class="n">readlines</span><span class="p">())</span>
<span class="k">if</span> <span class="n">line</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="n">line</span><span class="p">[:</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span>
<span class="k">return</span> <span class="n">line</span>
<span class="k">if</span> <span class="n">fd</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">stdout</span><span class="o">.</span><span class="n">fileno</span><span class="p">():</span>
<span class="n">line</span> <span class="o">=</span> <span class="sa">b</span><span class="s1">&#39;&#39;</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">_proc</span><span class="o">.</span><span class="n">stdout</span><span class="o">.</span><span class="n">readlines</span><span class="p">())</span>
<span class="k">if</span> <span class="n">line</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="n">line</span><span class="p">[:</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span>
<span class="k">return</span> <span class="n">line</span></div>
<span class="nd">@staticmethod</span>
<div class="viewcode-block" id="_Dataflow._extract_job"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataflow_hook/index.html#airflow.contrib.hooks.gcp_dataflow_hook._Dataflow._extract_job">[docs]</a> <span class="k">def</span> <span class="nf">_extract_job</span><span class="p">(</span><span class="n">line</span><span class="p">):</span>
<span class="c1"># Job id info: https://goo.gl/SE29y9.</span>
<span class="n">job_id_pattern</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span>
<span class="sa">br</span><span class="s1">&#39;.*console.cloud.google.com/dataflow.*/jobs/([a-z|0-9|A-Z|\-|\_]+).*&#39;</span><span class="p">)</span>
<span class="n">matched_job</span> <span class="o">=</span> <span class="n">job_id_pattern</span><span class="o">.</span><span class="n">search</span><span class="p">(</span><span class="n">line</span> <span class="ow">or</span> <span class="s1">&#39;&#39;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">matched_job</span><span class="p">:</span>
<span class="k">return</span> <span class="n">matched_job</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span><span class="o">.</span><span class="n">decode</span><span class="p">()</span></div>
<div class="viewcode-block" id="_Dataflow.wait_for_done"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataflow_hook/index.html#airflow.contrib.hooks.gcp_dataflow_hook._Dataflow.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="n">reads</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">stderr</span><span class="o">.</span><span class="n">fileno</span><span class="p">(),</span> <span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">stdout</span><span class="o">.</span><span class="n">fileno</span><span class="p">()]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;Start waiting for DataFlow process to complete.&quot;</span><span class="p">)</span>
<span class="n">job_id</span> <span class="o">=</span> <span class="kc">None</span>
<span class="c1"># Make sure logs are processed regardless whether the subprocess is</span>
<span class="c1"># terminated.</span>
<span class="n">process_ends</span> <span class="o">=</span> <span class="kc">False</span>
<span class="k">while</span> <span class="kc">True</span><span class="p">:</span>
<span class="n">ret</span> <span class="o">=</span> <span class="n">select</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">reads</span><span class="p">,</span> <span class="p">[],</span> <span class="p">[],</span> <span class="mi">5</span><span class="p">)</span>
<span class="k">if</span> <span class="n">ret</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">for</span> <span class="n">fd</span> <span class="ow">in</span> <span class="n">ret</span><span class="p">[</span><span class="mi">0</span><span class="p">]:</span>
<span class="n">line</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_line</span><span class="p">(</span><span class="n">fd</span><span class="p">)</span>
<span class="k">if</span> <span class="n">line</span><span class="p">:</span>
<span class="n">job_id</span> <span class="o">=</span> <span class="n">job_id</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">_extract_job</span><span class="p">(</span><span class="n">line</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="s2">&quot;Waiting for DataFlow process to complete.&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">process_ends</span><span class="p">:</span>
<span class="k">break</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">poll</span><span class="p">()</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="c1"># Mark process completion but allows its outputs to be consumed.</span>
<span class="n">process_ends</span> <span class="o">=</span> <span class="kc">True</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">returncode</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span><span class="s2">&quot;DataFlow failed with return code </span><span class="si">{}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">returncode</span><span class="p">))</span>
<span class="k">return</span> <span class="n">job_id</span></div></div>
<div class="viewcode-block" id="DataFlowHook"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataflow_hook/index.html#airflow.contrib.hooks.gcp_dataflow_hook.DataFlowHook">[docs]</a><span class="k">class</span> <span class="nc">DataFlowHook</span><span class="p">(</span><span class="n">GoogleCloudBaseHook</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">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">poll_sleep</span><span class="o">=</span><span class="mi">10</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">poll_sleep</span> <span class="o">=</span> <span class="n">poll_sleep</span>
<span class="nb">super</span><span class="p">(</span><span class="n">DataFlowHook</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>
<div class="viewcode-block" id="DataFlowHook.get_conn"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataflow_hook/index.html#airflow.contrib.hooks.gcp_dataflow_hook.DataFlowHook.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;</span>
<span class="sd"> Returns a Google Cloud Dataflow service object.</span>
<span class="sd"> &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;dataflow&#39;</span><span class="p">,</span> <span class="s1">&#39;v1b3&#39;</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>
<span class="nd">@GoogleCloudBaseHook</span><span class="o">.</span><span class="n">_Decorators</span><span class="o">.</span><span class="n">provide_gcp_credential_file</span>
<div class="viewcode-block" id="DataFlowHook._start_dataflow"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataflow_hook/index.html#airflow.contrib.hooks.gcp_dataflow_hook.DataFlowHook._start_dataflow">[docs]</a> <span class="k">def</span> <span class="nf">_start_dataflow</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="n">name</span><span class="p">,</span> <span class="n">command_prefix</span><span class="p">,</span> <span class="n">label_formatter</span><span class="p">):</span>
<span class="n">variables</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set_variables</span><span class="p">(</span><span class="n">variables</span><span class="p">)</span>
<span class="n">cmd</span> <span class="o">=</span> <span class="n">command_prefix</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">_build_cmd</span><span class="p">(</span><span class="n">variables</span><span class="p">,</span> <span class="n">label_formatter</span><span class="p">)</span>
<span class="n">job_id</span> <span class="o">=</span> <span class="n">_Dataflow</span><span class="p">(</span><span class="n">cmd</span><span class="p">)</span><span class="o">.</span><span class="n">wait_for_done</span><span class="p">()</span>
<span class="n">_DataflowJob</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">variables</span><span class="p">[</span><span class="s1">&#39;project&#39;</span><span class="p">],</span> <span class="n">name</span><span class="p">,</span>
<span class="n">variables</span><span class="p">[</span><span class="s1">&#39;region&#39;</span><span class="p">],</span>
<span class="bp">self</span><span class="o">.</span><span class="n">poll_sleep</span><span class="p">,</span> <span class="n">job_id</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">num_retries</span><span class="p">)</span><span class="o">.</span><span class="n">wait_for_done</span><span class="p">()</span></div>
<span class="nd">@staticmethod</span>
<div class="viewcode-block" id="DataFlowHook._set_variables"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataflow_hook/index.html#airflow.contrib.hooks.gcp_dataflow_hook.DataFlowHook._set_variables">[docs]</a> <span class="k">def</span> <span class="nf">_set_variables</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="p">[</span><span class="s1">&#39;project&#39;</span><span class="p">]</span> <span class="ow">is</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="s1">&#39;Project not specified&#39;</span><span class="p">)</span>
<span class="k">if</span> <span class="s1">&#39;region&#39;</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">variables</span><span class="o">.</span><span class="n">keys</span><span class="p">():</span>
<span class="n">variables</span><span class="p">[</span><span class="s1">&#39;region&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">DEFAULT_DATAFLOW_LOCATION</span>
<span class="k">return</span> <span class="n">variables</span></div>
<div class="viewcode-block" id="DataFlowHook.start_java_dataflow"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataflow_hook/index.html#airflow.contrib.hooks.gcp_dataflow_hook.DataFlowHook.start_java_dataflow">[docs]</a> <span class="k">def</span> <span class="nf">start_java_dataflow</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">job_name</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">dataflow</span><span class="p">,</span> <span class="n">job_class</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">append_job_name</span><span class="o">=</span><span class="kc">True</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">_build_dataflow_job_name</span><span class="p">(</span><span class="n">job_name</span><span class="p">,</span> <span class="n">append_job_name</span><span class="p">)</span>
<span class="n">variables</span><span class="p">[</span><span class="s1">&#39;jobName&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">name</span>
<span class="k">def</span> <span class="nf">label_formatter</span><span class="p">(</span><span class="n">labels_dict</span><span class="p">):</span>
<span class="k">return</span> <span class="p">[</span><span class="s1">&#39;--labels=</span><span class="si">{}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="n">labels_dict</span><span class="p">)</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">&#39; &#39;</span><span class="p">,</span> <span class="s1">&#39;&#39;</span><span class="p">))]</span>
<span class="n">command_prefix</span> <span class="o">=</span> <span class="p">([</span><span class="s2">&quot;java&quot;</span><span class="p">,</span> <span class="s2">&quot;-cp&quot;</span><span class="p">,</span> <span class="n">dataflow</span><span class="p">,</span> <span class="n">job_class</span><span class="p">]</span> <span class="k">if</span> <span class="n">job_class</span>
<span class="k">else</span> <span class="p">[</span><span class="s2">&quot;java&quot;</span><span class="p">,</span> <span class="s2">&quot;-jar&quot;</span><span class="p">,</span> <span class="n">dataflow</span><span class="p">])</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_start_dataflow</span><span class="p">(</span><span class="n">variables</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">command_prefix</span><span class="p">,</span> <span class="n">label_formatter</span><span class="p">)</span></div>
<div class="viewcode-block" id="DataFlowHook.start_template_dataflow"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataflow_hook/index.html#airflow.contrib.hooks.gcp_dataflow_hook.DataFlowHook.start_template_dataflow">[docs]</a> <span class="k">def</span> <span class="nf">start_template_dataflow</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">job_name</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">parameters</span><span class="p">,</span> <span class="n">dataflow_template</span><span class="p">,</span>
<span class="n">append_job_name</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="n">variables</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set_variables</span><span class="p">(</span><span class="n">variables</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">_build_dataflow_job_name</span><span class="p">(</span><span class="n">job_name</span><span class="p">,</span> <span class="n">append_job_name</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_start_template_dataflow</span><span class="p">(</span>
<span class="n">name</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">parameters</span><span class="p">,</span> <span class="n">dataflow_template</span><span class="p">)</span></div>
<div class="viewcode-block" id="DataFlowHook.start_python_dataflow"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataflow_hook/index.html#airflow.contrib.hooks.gcp_dataflow_hook.DataFlowHook.start_python_dataflow">[docs]</a> <span class="k">def</span> <span class="nf">start_python_dataflow</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">job_name</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">dataflow</span><span class="p">,</span> <span class="n">py_options</span><span class="p">,</span>
<span class="n">append_job_name</span><span class="o">=</span><span class="kc">True</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">_build_dataflow_job_name</span><span class="p">(</span><span class="n">job_name</span><span class="p">,</span> <span class="n">append_job_name</span><span class="p">)</span>
<span class="n">variables</span><span class="p">[</span><span class="s1">&#39;job_name&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">name</span>
<span class="k">def</span> <span class="nf">label_formatter</span><span class="p">(</span><span class="n">labels_dict</span><span class="p">):</span>
<span class="k">return</span> <span class="p">[</span><span class="s1">&#39;--labels=</span><span class="si">{}</span><span class="s1">=</span><span class="si">{}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">key</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span>
<span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="n">labels_dict</span><span class="o">.</span><span class="n">items</span><span class="p">()]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_start_dataflow</span><span class="p">(</span><span class="n">variables</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="p">[</span><span class="s2">&quot;python2&quot;</span><span class="p">]</span> <span class="o">+</span> <span class="n">py_options</span> <span class="o">+</span> <span class="p">[</span><span class="n">dataflow</span><span class="p">],</span>
<span class="n">label_formatter</span><span class="p">)</span></div>
<span class="nd">@staticmethod</span>
<div class="viewcode-block" id="DataFlowHook._build_dataflow_job_name"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataflow_hook/index.html#airflow.contrib.hooks.gcp_dataflow_hook.DataFlowHook._build_dataflow_job_name">[docs]</a> <span class="k">def</span> <span class="nf">_build_dataflow_job_name</span><span class="p">(</span><span class="n">job_name</span><span class="p">,</span> <span class="n">append_job_name</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="n">base_job_name</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">job_name</span><span class="p">)</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">&#39;_&#39;</span><span class="p">,</span> <span class="s1">&#39;-&#39;</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">re</span><span class="o">.</span><span class="n">match</span><span class="p">(</span><span class="sa">r</span><span class="s2">&quot;^[a-z]([-a-z0-9]*[a-z0-9])?$&quot;</span><span class="p">,</span> <span class="n">base_job_name</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s1">&#39;Invalid job_name (</span><span class="si">{}</span><span class="s1">); the name must consist of&#39;</span>
<span class="s1">&#39;only the characters [-a-z0-9], starting with a &#39;</span>
<span class="s1">&#39;letter and ending with a letter or number &#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">base_job_name</span><span class="p">))</span>
<span class="k">if</span> <span class="n">append_job_name</span><span class="p">:</span>
<span class="n">safe_job_name</span> <span class="o">=</span> <span class="n">base_job_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>
<span class="k">else</span><span class="p">:</span>
<span class="n">safe_job_name</span> <span class="o">=</span> <span class="n">base_job_name</span>
<span class="k">return</span> <span class="n">safe_job_name</span></div>
<span class="nd">@staticmethod</span>
<div class="viewcode-block" id="DataFlowHook._build_cmd"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataflow_hook/index.html#airflow.contrib.hooks.gcp_dataflow_hook.DataFlowHook._build_cmd">[docs]</a> <span class="k">def</span> <span class="nf">_build_cmd</span><span class="p">(</span><span class="n">variables</span><span class="p">,</span> <span class="n">label_formatter</span><span class="p">):</span>
<span class="n">command</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;--runner=DataflowRunner&quot;</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="k">for</span> <span class="n">attr</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="n">variables</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
<span class="k">if</span> <span class="n">attr</span> <span class="o">==</span> <span class="s1">&#39;labels&#39;</span><span class="p">:</span>
<span class="n">command</span> <span class="o">+=</span> <span class="n">label_formatter</span><span class="p">(</span><span class="n">value</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">value</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">value</span><span class="o">.</span><span class="fm">__len__</span><span class="p">()</span> <span class="o">&lt;</span> <span class="mi">1</span><span class="p">:</span>
<span class="n">command</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s2">&quot;--&quot;</span> <span class="o">+</span> <span class="n">attr</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">command</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s2">&quot;--&quot;</span> <span class="o">+</span> <span class="n">attr</span> <span class="o">+</span> <span class="s2">&quot;=&quot;</span> <span class="o">+</span> <span class="n">value</span><span class="p">)</span>
<span class="k">return</span> <span class="n">command</span></div>
<div class="viewcode-block" id="DataFlowHook._start_template_dataflow"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataflow_hook/index.html#airflow.contrib.hooks.gcp_dataflow_hook.DataFlowHook._start_template_dataflow">[docs]</a> <span class="k">def</span> <span class="nf">_start_template_dataflow</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="n">variables</span><span class="p">,</span> <span class="n">parameters</span><span class="p">,</span>
<span class="n">dataflow_template</span><span class="p">):</span>
<span class="c1"># Builds RuntimeEnvironment from variables dictionary</span>
<span class="c1"># https://cloud.google.com/dataflow/docs/reference/rest/v1b3/RuntimeEnvironment</span>
<span class="n">environment</span> <span class="o">=</span> <span class="p">{}</span>
<span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">&#39;numWorkers&#39;</span><span class="p">,</span> <span class="s1">&#39;maxWorkers&#39;</span><span class="p">,</span> <span class="s1">&#39;zone&#39;</span><span class="p">,</span> <span class="s1">&#39;serviceAccountEmail&#39;</span><span class="p">,</span>
<span class="s1">&#39;tempLocation&#39;</span><span class="p">,</span> <span class="s1">&#39;bypassTempDirValidation&#39;</span><span class="p">,</span> <span class="s1">&#39;machineType&#39;</span><span class="p">,</span>
<span class="s1">&#39;additionalExperiments&#39;</span><span class="p">,</span> <span class="s1">&#39;network&#39;</span><span class="p">,</span> <span class="s1">&#39;subnetwork&#39;</span><span class="p">,</span> <span class="s1">&#39;additionalUserLabels&#39;</span><span class="p">]:</span>
<span class="k">if</span> <span class="n">key</span> <span class="ow">in</span> <span class="n">variables</span><span class="p">:</span>
<span class="n">environment</span><span class="o">.</span><span class="n">update</span><span class="p">({</span><span class="n">key</span><span class="p">:</span> <span class="n">variables</span><span class="p">[</span><span class="n">key</span><span class="p">]})</span>
<span class="n">body</span> <span class="o">=</span> <span class="p">{</span><span class="s2">&quot;jobName&quot;</span><span class="p">:</span> <span class="n">name</span><span class="p">,</span>
<span class="s2">&quot;parameters&quot;</span><span class="p">:</span> <span class="n">parameters</span><span class="p">,</span>
<span class="s2">&quot;environment&quot;</span><span class="p">:</span> <span class="n">environment</span><span class="p">}</span>
<span class="n">service</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span>
<span class="n">request</span> <span class="o">=</span> <span class="n">service</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">locations</span><span class="p">()</span><span class="o">.</span><span class="n">templates</span><span class="p">()</span><span class="o">.</span><span class="n">launch</span><span class="p">(</span>
<span class="n">projectId</span><span class="o">=</span><span class="n">variables</span><span class="p">[</span><span class="s1">&#39;project&#39;</span><span class="p">],</span>
<span class="n">location</span><span class="o">=</span><span class="n">variables</span><span class="p">[</span><span class="s1">&#39;region&#39;</span><span class="p">],</span>
<span class="n">gcsPath</span><span class="o">=</span><span class="n">dataflow_template</span><span class="p">,</span>
<span class="n">body</span><span class="o">=</span><span class="n">body</span>
<span class="p">)</span>
<span class="n">response</span> <span class="o">=</span> <span class="n">request</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="bp">self</span><span class="o">.</span><span class="n">num_retries</span><span class="p">)</span>
<span class="n">variables</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set_variables</span><span class="p">(</span><span class="n">variables</span><span class="p">)</span>
<span class="n">_DataflowJob</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">variables</span><span class="p">[</span><span class="s1">&#39;project&#39;</span><span class="p">],</span> <span class="n">name</span><span class="p">,</span> <span class="n">variables</span><span class="p">[</span><span class="s1">&#39;region&#39;</span><span class="p">],</span>
<span class="bp">self</span><span class="o">.</span><span class="n">poll_sleep</span><span class="p">,</span> <span class="n">num_retries</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">num_retries</span><span class="p">)</span><span class="o">.</span><span class="n">wait_for_done</span><span class="p">()</span>
<span class="k">return</span> <span class="n">response</span></div></div>
</pre></div>
</div>
</div>
<footer>
<hr/>
<div role="contentinfo">
<p>
</p>
</div>
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
<div class="footer">This page uses <a href="https://analytics.google.com/">
Google Analytics</a> to collect statistics. You can disable it by blocking
the JavaScript coming from www.google-analytics.com. Check our
<a href="../../../../privacy_notice.html">Privacy Policy</a>
for more details.
<script type="text/javascript">
(function() {
var ga = document.createElement('script');
ga.src = ('https:' == document.location.protocol ?
'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
ga.setAttribute('async', 'true');
var nodes = document.documentElement.childNodes;
var i = -1;
var node;
do {
i++;
node = nodes[i]
} while(node.nodeType !== Node.ELEMENT_NODE);
node.appendChild(ga);
})();
</script>
</div>
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>