| |
| |
| <!-- |
| 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_dataproc_hook — 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/jira-links.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="stylesheet" href="../../../../_static/exampleinclude.css" type="text/css" /> |
| <link rel="index" title="Index" href="../../../../genindex.html" /> |
| <link rel="search" title="Search" href="../../../../search.html" /> |
| |
| <script> |
| </script> |
| <style> |
| |
| </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"> |
| 1.10.8 |
| </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 & Triggers</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../executor/index.html">Executor</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="../../../../dag-serialization.html">DAG Serialization</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="../../../../best-practices.html">Best Practices</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="../../../../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> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../configurations-ref.html">Configurations</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> »</li> |
| |
| <li><a href="../../../index.html">Module code</a> »</li> |
| |
| <li><a href="../hooks.html">airflow.contrib.hooks</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">googleapiclient.discovery</span> <span class="kn">import</span> <span class="n">build</span> |
| <span class="kn">from</span> <span class="nn">zope.deprecation</span> <span class="kn">import</span> <span class="n">deprecation</span> |
| |
| <span class="kn">from</span> <span class="nn">airflow.version</span> <span class="kn">import</span> <span class="n">version</span> |
| <span class="kn">from</span> <span class="nn">airflow.contrib.hooks.gcp_api_base_hook</span> <span class="kn">import</span> <span class="n">GoogleCloudBaseHook</span> |
| <span class="kn">from</span> <span class="nn">airflow.utils.log.logging_mixin</span> <span class="kn">import</span> <span class="n">LoggingMixin</span> |
| |
| |
| <div class="viewcode-block" id="_DataProcJob"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJob">[docs]</a><span class="k">class</span> <span class="nc">_DataProcJob</span><span class="p">(</span><span class="n">LoggingMixin</span><span class="p">):</span> |
| <span class="k">def</span> <span class="fm">__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="n">job_error_states</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="mi">5</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">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_error_states</span> <span class="o">=</span> <span class="n">job_error_states</span> |
| |
| <span class="c1"># Check if the job to submit is already running on the cluster.</span> |
| <span class="c1"># If so, don't resubmit the job.</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">cluster_name</span> <span class="o">=</span> <span class="n">job</span><span class="p">[</span><span class="s1">'job'</span><span class="p">][</span><span class="s1">'placement'</span><span class="p">][</span><span class="s1">'clusterName'</span><span class="p">]</span> |
| <span class="k">except</span> <span class="ne">KeyError</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">'Job to submit is incorrectly configured.'</span><span class="p">)</span> |
| <span class="k">raise</span> |
| |
| <span class="n">jobs_on_cluster_response</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">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_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">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">UUID_LENGTH</span> <span class="o">=</span> <span class="mi">9</span> |
| <span class="n">jobs_on_cluster</span> <span class="o">=</span> <span class="n">jobs_on_cluster_response</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'jobs'</span><span class="p">,</span> <span class="p">[])</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">task_id_to_submit</span> <span class="o">=</span> <span class="n">job</span><span class="p">[</span><span class="s1">'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="o">-</span><span class="n">UUID_LENGTH</span><span class="p">]</span> |
| <span class="k">except</span> <span class="ne">KeyError</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">'Job to submit is incorrectly configured.'</span><span class="p">)</span> |
| <span class="k">raise</span> |
| |
| <span class="c1"># There is a small set of states that we will accept as sufficient</span> |
| <span class="c1"># for attaching the new task instance to the old Dataproc job. We</span> |
| <span class="c1"># generally err on the side of _not_ attaching, unless the prior</span> |
| <span class="c1"># job is in a known-good state. For example, we don't attach to an</span> |
| <span class="c1"># ERRORed job because we want Airflow to be able to retry the job.</span> |
| <span class="c1"># The full set of possible states is here:</span> |
| <span class="c1"># https://cloud.google.com/dataproc/docs/reference/rest/v1beta2/projects.regions.jobs#State</span> |
| <span class="n">recoverable_states</span> <span class="o">=</span> <span class="nb">frozenset</span><span class="p">([</span> |
| <span class="s1">'PENDING'</span><span class="p">,</span> |
| <span class="s1">'SETUP_DONE'</span><span class="p">,</span> |
| <span class="s1">'RUNNING'</span><span class="p">,</span> |
| <span class="s1">'DONE'</span><span class="p">,</span> |
| <span class="p">])</span> |
| |
| <span class="n">found_match</span> <span class="o">=</span> <span class="kc">False</span> |
| <span class="k">for</span> <span class="n">job_on_cluster</span> <span class="ow">in</span> <span class="n">jobs_on_cluster</span><span class="p">:</span> |
| <span class="n">job_on_cluster_id</span> <span class="o">=</span> <span class="n">job_on_cluster</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="n">job_on_cluster_task_id</span> <span class="o">=</span> <span class="n">job_on_cluster_id</span><span class="p">[:</span><span class="o">-</span><span class="n">UUID_LENGTH</span><span class="p">]</span> |
| <span class="k">if</span> <span class="n">task_id_to_submit</span> <span class="o">==</span> <span class="n">job_on_cluster_task_id</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="n">job_on_cluster</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="n">found_match</span> <span class="o">=</span> <span class="kc">True</span> |
| |
| <span class="c1"># We can stop looking once we find a matching job in a recoverable state.</span> |
| <span class="k">if</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="ow">in</span> <span class="n">recoverable_states</span><span class="p">:</span> |
| <span class="k">break</span> |
| |
| <span class="k">if</span> <span class="n">found_match</span> <span class="ow">and</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="ow">in</span> <span class="n">recoverable_states</span><span class="p">:</span> |
| <span class="n">message</span> <span class="o">=</span> <span class="s2">"""</span> |
| <span class="s2"> Reattaching to previously-started DataProc job </span><span class="si">%s</span><span class="s2"> (in state </span><span class="si">%s</span><span class="s2">).</span> |
| <span class="s2"> If this is not the desired behavior (ie if you would like to re-run this job),</span> |
| <span class="s2"> please delete the previous instance of the job by running:</span> |
| |
| <span class="s2"> gcloud --project </span><span class="si">%s</span><span class="s2"> dataproc jobs delete </span><span class="si">%s</span><span class="s2"> --region </span><span class="si">%s</span><span class="s2"></span> |
| <span class="s2">"""</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">message</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="bp">self</span><span class="o">.</span><span class="n">project_id</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">region</span><span class="p">,</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="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="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="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> |
| |
| <div class="viewcode-block" id="_DataProcJob.wait_for_done"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJob.wait_for_done">[docs]</a> <span class="k">def</span> <span class="nf">wait_for_done</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">while</span> <span class="kc">True</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">job</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_api</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">regions</span><span class="p">()</span><span class="o">.</span><span class="n">jobs</span><span class="p">()</span><span class="o">.</span><span class="n">get</span><span class="p">(</span> |
| <span class="n">projectId</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">project_id</span><span class="p">,</span> |
| <span class="n">region</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">region</span><span class="p">,</span> |
| <span class="n">jobId</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">job_id</span><span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">num_retries</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">num_retries</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="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="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></div> |
| |
| <div class="viewcode-block" id="_DataProcJob.raise_error"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJob.raise_error">[docs]</a> <span class="k">def</span> <span class="nf">raise_error</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">message</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="n">job_state</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s1">'status'</span><span class="p">][</span><span class="s1">'state'</span><span class="p">]</span> |
| <span class="c1"># We always consider ERROR to be an error state.</span> |
| <span class="k">if</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">job_error_states</span> <span class="ow">and</span> <span class="n">job_state</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">job_error_states</span><span class="p">)</span> <span class="ow">or</span> <span class="s1">'ERROR'</span> <span class="o">==</span> <span class="n">job_state</span><span class="p">:</span> |
| <span class="n">ex_message</span> <span class="o">=</span> <span class="n">message</span> <span class="ow">or</span> <span class="p">(</span><span class="s2">"Google DataProc job has state: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="n">job_state</span><span class="p">)</span> |
| <span class="n">ex_details</span> <span class="o">=</span> <span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s1">'status'</span><span class="p">][</span><span class="s1">'details'</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="k">else</span> <span class="s2">"No details available"</span><span class="p">)</span> |
| <span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span><span class="n">ex_message</span> <span class="o">+</span> <span class="s2">": "</span> <span class="o">+</span> <span class="n">ex_details</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="_DataProcJob.get"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJob.get">[docs]</a> <span class="k">def</span> <span class="nf">get</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">job</span></div></div> |
| |
| |
| <div class="viewcode-block" id="_DataProcJobBuilder"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder">[docs]</a><span class="k">class</span> <span class="nc">_DataProcJobBuilder</span><span class="p">:</span> |
| <span class="k">def</span> <span class="fm">__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">uuid4</span><span class="p">())[:</span><span class="mi">8</span><span class="p">]</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">job_type</span> <span class="o">=</span> <span class="n">job_type</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">job</span> <span class="o">=</span> <span class="p">{</span> |
| <span class="s2">"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="s2">"labels"</span><span class="p">:</span> <span class="p">{</span><span class="s1">'airflow-version'</span><span class="p">:</span> <span class="s1">'v'</span> <span class="o">+</span> <span class="n">version</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">'.'</span><span class="p">,</span> <span class="s1">'-'</span><span class="p">)</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">'+'</span><span class="p">,</span> <span class="s1">'-'</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> |
| |
| <div class="viewcode-block" id="_DataProcJobBuilder.add_labels"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.add_labels">[docs]</a> <span class="k">def</span> <span class="nf">add_labels</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">labels</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Set labels for Dataproc job.</span> |
| |
| <span class="sd"> :param labels: Labels for the job query.</span> |
| <span class="sd"> :type labels: dict</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">labels</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">"labels"</span><span class="p">]</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">labels</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="_DataProcJobBuilder.add_variables"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.add_variables">[docs]</a> <span class="k">def</span> <span class="nf">add_variables</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">variables</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">variables</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s2">"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></div> |
| |
| <div class="viewcode-block" id="_DataProcJobBuilder.add_args"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.add_args">[docs]</a> <span class="k">def</span> <span class="nf">add_args</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">args</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">args</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s2">"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></div> |
| |
| <div class="viewcode-block" id="_DataProcJobBuilder.add_query"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.add_query">[docs]</a> <span class="k">def</span> <span class="nf">add_query</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s2">"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></div> |
| |
| <div class="viewcode-block" id="_DataProcJobBuilder.add_query_uri"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.add_query_uri">[docs]</a> <span class="k">def</span> <span class="nf">add_query_uri</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query_uri</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s2">"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></div> |
| |
| <div class="viewcode-block" id="_DataProcJobBuilder.add_jar_file_uris"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.add_jar_file_uris">[docs]</a> <span class="k">def</span> <span class="nf">add_jar_file_uris</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">jars</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">jars</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s2">"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></div> |
| |
| <div class="viewcode-block" id="_DataProcJobBuilder.add_archive_uris"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.add_archive_uris">[docs]</a> <span class="k">def</span> <span class="nf">add_archive_uris</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">archives</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">archives</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s2">"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></div> |
| |
| <div class="viewcode-block" id="_DataProcJobBuilder.add_file_uris"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.add_file_uris">[docs]</a> <span class="k">def</span> <span class="nf">add_file_uris</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">files</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">files</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s2">"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></div> |
| |
| <div class="viewcode-block" id="_DataProcJobBuilder.add_python_file_uris"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.add_python_file_uris">[docs]</a> <span class="k">def</span> <span class="nf">add_python_file_uris</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pyfiles</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">pyfiles</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s2">"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></div> |
| |
| <div class="viewcode-block" id="_DataProcJobBuilder.set_main"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.set_main">[docs]</a> <span class="k">def</span> <span class="nf">set_main</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">main_jar</span><span class="p">,</span> <span class="n">main_class</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">main_class</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">main_jar</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span><span class="s2">"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></div> |
| |
| <div class="viewcode-block" id="_DataProcJobBuilder.set_python_main"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.set_python_main">[docs]</a> <span class="k">def</span> <span class="nf">set_python_main</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">main</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s2">"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></div> |
| |
| <div class="viewcode-block" id="_DataProcJobBuilder.set_job_name"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.set_job_name">[docs]</a> <span class="k">def</span> <span class="nf">set_job_name</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">job</span><span class="p">[</span><span class="s2">"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">uuid4</span><span class="p">())[:</span><span class="mi">8</span><span class="p">]</span></div> |
| |
| <div class="viewcode-block" id="_DataProcJobBuilder.build"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcJobBuilder.build">[docs]</a> <span class="k">def</span> <span class="nf">build</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">job</span></div></div> |
| |
| |
| <div class="viewcode-block" id="_DataProcOperation"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcOperation">[docs]</a><span class="k">class</span> <span class="nc">_DataProcOperation</span><span class="p">(</span><span class="n">LoggingMixin</span><span class="p">):</span> |
| <span class="sd">"""Continuously polls Dataproc Operation until it completes."""</span> |
| <span class="k">def</span> <span class="fm">__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="n">num_retries</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="bp">self</span><span class="o">.</span><span class="n">num_retries</span> <span class="o">=</span> <span class="n">num_retries</span> |
| |
| <div class="viewcode-block" id="_DataProcOperation.wait_for_done"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcOperation.wait_for_done">[docs]</a> <span class="k">def</span> <span class="nf">wait_for_done</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_check_done</span><span class="p">():</span> |
| <span class="k">return</span> <span class="kc">True</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span> |
| <span class="s1">'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="bp">self</span><span class="o">.</span><span class="n">num_retries</span><span class="p">))</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_check_done</span><span class="p">():</span> |
| <span class="k">return</span> <span class="kc">True</span></div> |
| |
| <div class="viewcode-block" id="_DataProcOperation.get"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcOperation.get">[docs]</a> <span class="k">def</span> <span class="nf">get</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">operation</span></div> |
| |
| <div class="viewcode-block" id="_DataProcOperation._check_done"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcOperation._check_done">[docs]</a> <span class="k">def</span> <span class="nf">_check_done</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">if</span> <span class="s1">'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></div> |
| |
| <div class="viewcode-block" id="_DataProcOperation._raise_error"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook._DataProcOperation._raise_error">[docs]</a> <span class="k">def</span> <span class="nf">_raise_error</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span><span class="s1">'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></div> |
| |
| |
| <div class="viewcode-block" id="DataProcHook"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook.DataProcHook">[docs]</a><span class="k">class</span> <span class="nc">DataProcHook</span><span class="p">(</span><span class="n">GoogleCloudBaseHook</span><span class="p">):</span> |
| <span class="sd">"""Hook for Google Cloud Dataproc APIs."""</span> |
| |
| <span class="k">def</span> <span class="fm">__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="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook.DataProcHook.get_conn">[docs]</a> <span class="k">def</span> <span class="nf">get_conn</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""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> |
| <span class="n">cache_discovery</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="DataProcHook.get_cluster"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook.DataProcHook.get_cluster">[docs]</a> <span class="k">def</span> <span class="nf">get_cluster</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">project_id</span><span class="p">,</span> <span class="n">region</span><span class="p">,</span> <span class="n">cluster_name</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">regions</span><span class="p">()</span><span class="o">.</span><span class="n">clusters</span><span class="p">()</span><span class="o">.</span><span class="n">get</span><span class="p">(</span> |
| <span class="n">projectId</span><span class="o">=</span><span class="n">project_id</span><span class="p">,</span> |
| <span class="n">region</span><span class="o">=</span><span class="n">region</span><span class="p">,</span> |
| <span class="n">clusterName</span><span class="o">=</span><span class="n">cluster_name</span> |
| <span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">num_retries</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">num_retries</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="DataProcHook.submit"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook.DataProcHook.submit">[docs]</a> <span class="k">def</span> <span class="nf">submit</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">project_id</span><span class="p">,</span> <span class="n">job</span><span class="p">,</span> <span class="n">region</span><span class="o">=</span><span class="s1">'global'</span><span class="p">,</span> <span class="n">job_error_states</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="n">submitted</span> <span class="o">=</span> <span class="n">_DataProcJob</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">(),</span> <span class="n">project_id</span><span class="p">,</span> <span class="n">job</span><span class="p">,</span> <span class="n">region</span><span class="p">,</span> |
| <span class="n">job_error_states</span><span class="o">=</span><span class="n">job_error_states</span><span class="p">,</span> |
| <span class="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">if</span> <span class="ow">not</span> <span class="n">submitted</span><span class="o">.</span><span class="n">wait_for_done</span><span class="p">():</span> |
| <span class="n">submitted</span><span class="o">.</span><span class="n">raise_error</span><span class="p">()</span></div> |
| |
| <div class="viewcode-block" id="DataProcHook.create_job_template"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook.DataProcHook.create_job_template">[docs]</a> <span class="k">def</span> <span class="nf">create_job_template</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">task_id</span><span class="p">,</span> <span class="n">cluster_name</span><span class="p">,</span> <span class="n">job_type</span><span class="p">,</span> <span class="n">properties</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">_DataProcJobBuilder</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">project_id</span><span class="p">,</span> <span class="n">task_id</span><span class="p">,</span> <span class="n">cluster_name</span><span class="p">,</span> |
| <span class="n">job_type</span><span class="p">,</span> <span class="n">properties</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="DataProcHook.wait"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook.DataProcHook.wait">[docs]</a> <span class="k">def</span> <span class="nf">wait</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">operation</span><span class="p">):</span> |
| <span class="sd">"""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="bp">self</span><span class="o">.</span><span class="n">num_retries</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 class="viewcode-block" id="DataProcHook.cancel"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/gcp_dataproc_hook/index.html#airflow.contrib.hooks.gcp_dataproc_hook.DataProcHook.cancel">[docs]</a> <span class="k">def</span> <span class="nf">cancel</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_id</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="sd">"""</span> |
| <span class="sd"> Cancel a Google Cloud DataProc job.</span> |
| <span class="sd"> :param project_id: Name of the project the job belongs to</span> |
| <span class="sd"> :type project_id: str</span> |
| <span class="sd"> :param job_id: Identifier of the job to cancel</span> |
| <span class="sd"> :type job_id: int</span> |
| <span class="sd"> :param region: Region used for the job</span> |
| <span class="sd"> :type region: str</span> |
| <span class="sd"> :returns A Job json dictionary representing the canceled job</span> |
| <span class="sd"> """</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">jobs</span><span class="p">()</span><span class="o">.</span><span class="n">cancel</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">jobId</span><span class="o">=</span><span class="n">job_id</span></div></div> |
| <span class="p">)</span> |
| |
| |
| <span class="nb">setattr</span><span class="p">(</span> |
| <span class="n">DataProcHook</span><span class="p">,</span> |
| <span class="s2">"await"</span><span class="p">,</span> |
| <span class="n">deprecation</span><span class="o">.</span><span class="n">deprecated</span><span class="p">(</span> |
| <span class="n">DataProcHook</span><span class="o">.</span><span class="n">wait</span><span class="p">,</span> <span class="s2">"renamed to 'wait' for Python3.7 compatibility"</span> |
| <span class="p">),</span> |
| <span class="p">)</span> |
| </pre></div> |
| |
| </div> |
| |
| </div> |
| |
| |
| <footer> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| |
| </p> |
| </div> |
| Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| <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. |
| </div> |
| |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| |
| |
| |
| <!-- Theme Analytics --> |
| <script> |
| (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ |
| (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o), |
| m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) |
| })(window,document,'script','https://www.google-analytics.com/analytics.js','ga'); |
| |
| ga('create', 'UA-140539454-1', 'auto'); |
| ga('send', 'pageview'); |
| </script> |
| |
| |
| |
| |
| </body> |
| </html> |