You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@airflow.apache.org by ka...@apache.org on 2018/08/27 16:27:05 UTC
[45/51] [partial] incubator-airflow-site git commit: 1.10.0
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/11437c14/_modules/airflow/contrib/hooks/gcp_dataproc_hook.html
----------------------------------------------------------------------
diff --git a/_modules/airflow/contrib/hooks/gcp_dataproc_hook.html b/_modules/airflow/contrib/hooks/gcp_dataproc_hook.html
new file mode 100644
index 0000000..4ca7edd
--- /dev/null
+++ b/_modules/airflow/contrib/hooks/gcp_dataproc_hook.html
@@ -0,0 +1,463 @@
+
+
+<!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 — Airflow Documentation</title>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
+
+
+
+
+
+ <link rel="index" title="Index"
+ href="../../../../genindex.html"/>
+ <link rel="search" title="Search" href="../../../../search.html"/>
+ <link rel="top" title="Airflow Documentation" href="../../../../index.html"/>
+ <link rel="up" title="Module code" href="../../../index.html"/>
+
+
+ <script src="../../../../_static/js/modernizr.min.js"></script>
+
+</head>
+
+<body class="wy-body-for-nav" role="document">
+
+
+ <div class="wy-grid-for-nav">
+
+
+ <nav data-toggle="wy-nav-shift" class="wy-nav-side">
+ <div class="wy-side-scroll">
+ <div class="wy-side-nav-search">
+
+
+
+ <a href="../../../../index.html" class="icon icon-home"> Airflow
+
+
+
+ </a>
+
+
+
+
+
+
+
+<div role="search">
+ <form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get">
+ <input type="text" name="q" placeholder="Search docs" />
+ <input type="hidden" name="check_keywords" value="yes" />
+ <input type="hidden" name="area" value="default" />
+ </form>
+</div>
+
+
+ </div>
+
+ <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
+
+
+
+
+
+
+ <ul>
+<li class="toctree-l1"><a class="reference internal" href="../../../../project.html">Project</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../license.html">License</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../start.html">Quick Start</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../installation.html">Installation</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../tutorial.html">Tutorial</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../howto/index.html">How-to Guides</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../ui.html">UI / Screenshots</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../concepts.html">Concepts</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../profiling.html">Data Profiling</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../cli.html">Command Line Interface</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling & Triggers</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../plugins.html">Plugins</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../security.html">Security</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../timezone.html">Time zones</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../api.html">Experimental Rest API</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../integration.html">Integration</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../lineage.html">Lineage</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../faq.html">FAQ</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../code.html">API Reference</a></li>
+</ul>
+
+
+
+ </div>
+ </div>
+ </nav>
+
+ <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
+
+
+ <nav class="wy-nav-top" role="navigation" aria-label="top navigation">
+
+ <i data-toggle="wy-nav-top" class="fa fa-bars"></i>
+ <a href="../../../../index.html">Airflow</a>
+
+ </nav>
+
+
+
+ <div class="wy-nav-content">
+ <div class="rst-content">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+<div role="navigation" aria-label="breadcrumbs navigation">
+
+ <ul class="wy-breadcrumbs">
+
+ <li><a href="../../../../index.html">Docs</a> »</li>
+
+ <li><a href="../../../index.html">Module code</a> »</li>
+
+ <li>airflow.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"># "License"); you may not use this file except in compliance</span>
+<span class="c1"># with the License. You may obtain a copy of the License at</span>
+<span class="c1"># </span>
+<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
+<span class="c1"># </span>
+<span class="c1"># Unless required by applicable law or agreed to in writing,</span>
+<span class="c1"># software distributed under the License is distributed on an</span>
+<span class="c1"># "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span>
+<span class="c1"># KIND, either express or implied. See the License for the</span>
+<span class="c1"># specific language governing permissions and limitations</span>
+<span class="c1"># under the License.</span>
+<span class="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">apiclient.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="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">'global'</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">'reference'</span><span class="p">][</span><span class="s1">'jobId'</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">'DataProc job </span><span class="si">%s</span><span class="s1"> is </span><span class="si">%s</span><span class="s1">'</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">'status'</span><span class="p">][</span><span class="s1">'state'</span><span class="p">])</span>
+ <span class="p">)</span>
+
+ <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">'ERROR'</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">'status'</span><span class="p">][</span><span class="s1">'state'</span><span class="p">]:</span>
+ <span class="nb">print</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="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">'DataProc job </span><span class="si">%s</span><span class="s1"> has errors'</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">'status'</span><span class="p">][</span><span class="s1">'details'</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">'CANCELLED'</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">'status'</span><span class="p">][</span><span class="s1">'state'</span><span class="p">]:</span>
+ <span class="nb">print</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="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">'DataProc job </span><span class="si">%s</span><span class="s1"> is cancelled'</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">'details'</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">'status'</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">'status'</span><span class="p">][</span><span class="s1">'details'</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">'DONE'</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">'status'</span><span class="p">][</span><span class="s1">'state'</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">'DataProc job </span><span class="si">%s</span><span class="s1"> is </span><span class="si">%s</span><span class="s1">'</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">'status'</span><span class="p">][</span><span class="s1">'state'</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>
+
+ <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="k">if</span> <span class="s1">'ERROR'</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">'status'</span><span class="p">][</span><span class="s1">'state'</span><span class="p">]:</span>
+ <span class="k">if</span> <span class="n">message</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
+ <span class="n">message</span> <span class="o">=</span> <span class="s2">"Google DataProc job has error"</span>
+ <span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span><span class="n">message</span> <span class="o">+</span> <span class="s2">": "</span> <span class="o">+</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">'status'</span><span class="p">][</span><span class="s1">'details'</span><span class="p">]))</span>
+
+ <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>
+
+
+<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">"_"</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">uuid1</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">"job"</span><span class="p">:</span> <span class="p">{</span>
+ <span class="s2">"reference"</span><span class="p">:</span> <span class="p">{</span>
+ <span class="s2">"projectId"</span><span class="p">:</span> <span class="n">project_id</span><span class="p">,</span>
+ <span class="s2">"jobId"</span><span class="p">:</span> <span class="n">name</span><span class="p">,</span>
+ <span class="p">},</span>
+ <span class="s2">"placement"</span><span class="p">:</span> <span class="p">{</span>
+ <span class="s2">"clusterName"</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">"job"</span><span class="p">][</span><span class="n">job_type</span><span class="p">][</span><span class="s2">"properties"</span><span class="p">]</span> <span class="o">=</span> <span class="n">properties</span>
+
+ <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">"job"</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">"scriptVariables"</span><span class="p">]</span> <span class="o">=</span> <span class="n">variables</span>
+
+ <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">"job"</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">"args"</span><span class="p">]</span> <span class="o">=</span> <span class="n">args</span>
+
+ <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">"job"</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">"queryList"</span><span class="p">]</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'queries'</span><span class="p">:</span> <span class="p">[</span><span class="n">query</span><span class="p">]}</span>
+
+ <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">"job"</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">"queryFileUri"</span><span class="p">]</span> <span class="o">=</span> <span class="n">query_uri</span>
+
+ <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">"job"</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">"jarFileUris"</span><span class="p">]</span> <span class="o">=</span> <span class="n">jars</span>
+
+ <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">"job"</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">"archiveUris"</span><span class="p">]</span> <span class="o">=</span> <span class="n">archives</span>
+
+ <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">"job"</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">"fileUris"</span><span class="p">]</span> <span class="o">=</span> <span class="n">files</span>
+
+ <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">"job"</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">"pythonFileUris"</span><span class="p">]</span> <span class="o">=</span> <span class="n">pyfiles</span>
+
+ <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">"Set either main_jar or main_class"</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">"job"</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">"mainJarFileUri"</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">"job"</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">"mainClass"</span><span class="p">]</span> <span class="o">=</span> <span class="n">main_class</span>
+
+ <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">"job"</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">"mainPythonFileUri"</span><span class="p">]</span> <span class="o">=</span> <span class="n">main</span>
+
+ <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">"job"</span><span class="p">][</span><span class="s2">"reference"</span><span class="p">][</span><span class="s2">"jobId"</span><span class="p">]</span> <span class="o">=</span> <span class="n">name</span> <span class="o">+</span> <span class="s2">"_"</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">uuid1</span><span class="p">())[:</span><span class="mi">8</span><span class="p">]</span>
+
+ <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>
+
+
+<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">"""Continuously polls Dataproc Operation until it completes."""</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">'name'</span><span class="p">]</span>
+
+ <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">'Waiting for Dataproc Operation </span><span class="si">%s</span><span class="s1"> to finish'</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>
+
+ <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>
+
+ <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">'done'</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">'error'</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">'Dataproc Operation </span><span class="si">%s</span><span class="s1"> failed with error: </span><span class="si">%s</span><span class="s1">'</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">'error'</span><span class="p">][</span><span class="s1">'message'</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">'Dataproc Operation </span><span class="si">%s</span><span class="s1"> done'</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">'name'</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>
+
+ <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">'Google Dataproc Operation </span><span class="si">%s</span><span class="s1"> failed: </span><span class="si">%s</span><span class="s1">'</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">'error'</span><span class="p">][</span><span class="s1">'message'</span><span class="p">]))</span>
+
+
+<div class="viewcode-block" id="DataProcHook"><a class="viewcode-back" href="../../../../code.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">"""Hook for Google Cloud Dataproc APIs."""</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">'google_cloud_default'</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">'v1beta2'</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="../../../../code.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">"""Returns a Google Cloud Dataproc service object."""</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">'dataproc'</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></div>
+
+ <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>
+
+ <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">'global'</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="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><span class="s1">'DataProcTask has errors'</span><span class="p">)</span>
+
+ <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 class="viewcode-block" id="DataProcHook.await"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.hooks.gcp_dataproc_hook.DataProcHook.await">[docs]</a> <span class="k">def</span> <span class="nf">await</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">"""Awaits for Google Cloud Dataproc Operation to complete."""</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>
+</pre></div>
+
+ </div>
+ <div class="articleComments">
+
+ </div>
+ </div>
+ <footer>
+
+
+ <hr/>
+
+ <div role="contentinfo">
+ <p>
+
+ </p>
+ </div>
+ Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
+
+</footer>
+
+ </div>
+ </div>
+
+ </section>
+
+ </div>
+
+
+
+
+
+ <script type="text/javascript">
+ var DOCUMENTATION_OPTIONS = {
+ URL_ROOT:'../../../../',
+ VERSION:'',
+ COLLAPSE_INDEX:false,
+ FILE_SUFFIX:'.html',
+ HAS_SOURCE: true,
+ SOURCELINK_SUFFIX: '.txt'
+ };
+ </script>
+ <script type="text/javascript" src="../../../../_static/jquery.js"></script>
+ <script type="text/javascript" src="../../../../_static/underscore.js"></script>
+ <script type="text/javascript" src="../../../../_static/doctools.js"></script>
+
+
+
+
+
+ <script type="text/javascript" src="../../../../_static/js/theme.js"></script>
+
+
+
+
+ <script type="text/javascript">
+ jQuery(function () {
+ SphinxRtdTheme.StickyNav.enable();
+ });
+ </script>
+
+
+</body>
+</html>
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/11437c14/_modules/airflow/contrib/hooks/gcp_mlengine_hook.html
----------------------------------------------------------------------
diff --git a/_modules/airflow/contrib/hooks/gcp_mlengine_hook.html b/_modules/airflow/contrib/hooks/gcp_mlengine_hook.html
index 82450ae..df9ea25 100644
--- a/_modules/airflow/contrib/hooks/gcp_mlengine_hook.html
+++ b/_modules/airflow/contrib/hooks/gcp_mlengine_hook.html
@@ -91,7 +91,7 @@
<li class="toctree-l1"><a class="reference internal" href="../../../../start.html">Quick Start</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../installation.html">Installation</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../tutorial.html">Tutorial</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../../../configuration.html">Configuration</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../howto/index.html">How-to Guides</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../ui.html">UI / Screenshots</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../concepts.html">Concepts</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../profiling.html">Data Profiling</a></li>
@@ -99,8 +99,10 @@
<li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling & Triggers</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../plugins.html">Plugins</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../security.html">Security</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../timezone.html">Time zones</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../api.html">Experimental Rest API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../integration.html">Integration</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../lineage.html">Lineage</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../faq.html">FAQ</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../code.html">API Reference</a></li>
</ul>
@@ -236,14 +238,14 @@
<span class="sd"> :type project_id: string</span>
<span class="sd"> :param job: MLEngine Job object that should be provided to the MLEngine</span>
-<span class="sd"> API, such as:</span>
-<span class="sd"> {</span>
-<span class="sd"> 'jobId': 'my_job_id',</span>
-<span class="sd"> 'trainingInput': {</span>
-<span class="sd"> 'scaleTier': 'STANDARD_1',</span>
-<span class="sd"> ...</span>
-<span class="sd"> }</span>
-<span class="sd"> }</span>
+<span class="sd"> API, such as: ::</span>
+<span class="sd"> {</span>
+<span class="sd"> 'jobId': 'my_job_id',</span>
+<span class="sd"> 'trainingInput': {</span>
+<span class="sd"> 'scaleTier': 'STANDARD_1',</span>
+<span class="sd"> ...</span>
+<span class="sd"> }</span>
+<span class="sd"> }</span>
<span class="sd"> :type job: dict</span>
<span class="sd"> :param use_existing_job_fn: In case that a MLEngine job with the same</span>