| |
| |
| |
| |
| <!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.operators.dataproc_operator — Airflow Documentation</title> |
| |
| |
| |
| |
| |
| |
| |
| |
| <script type="text/javascript" src="../../../../_static/js/modernizr.min.js"></script> |
| |
| |
| <script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script> |
| <script type="text/javascript" src="../../../../_static/jquery.js"></script> |
| <script type="text/javascript" src="../../../../_static/underscore.js"></script> |
| <script type="text/javascript" src="../../../../_static/doctools.js"></script> |
| <script type="text/javascript" src="../../../../_static/language_data.js"></script> |
| |
| <script type="text/javascript" src="../../../../_static/js/theme.js"></script> |
| |
| |
| |
| |
| <link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" /> |
| <link rel="index" title="Index" href="../../../../genindex.html" /> |
| <link rel="search" title="Search" href="../../../../search.html" /> |
| |
| <script> |
| document.addEventListener('DOMContentLoaded', function() { |
| var el = document.getElementById('changelog'); |
| if (el !== null ) { |
| // [AIRFLOW-...] |
| el.innerHTML = el.innerHTML.replace( |
| /\[(AIRFLOW-[\d]+)\]/g, |
| `<a href="https://issues.apache.org/jira/browse/$1">[$1]</a>` |
| ); |
| // (#...) |
| el.innerHTML = el.innerHTML.replace( |
| /\(#([\d]+)\)/g, |
| `<a href="https://github.com/apache/airflow/pull/$1">(#$1)</a>` |
| ); |
| }; |
| }) |
| </script> |
| <style> |
| .example-header { |
| position: relative; |
| background: #9AAA7A; |
| padding: 8px 16px; |
| margin-bottom: 0; |
| } |
| .example-header--with-button { |
| padding-right: 166px; |
| } |
| .example-header:after{ |
| content: ''; |
| display: table; |
| clear: both; |
| } |
| .example-title { |
| display:block; |
| padding: 4px; |
| margin-right: 16px; |
| color: white; |
| overflow-x: auto; |
| } |
| .example-header-button { |
| top: 8px; |
| right: 16px; |
| position: absolute; |
| } |
| .example-header + .highlight-python { |
| margin-top: 0 !important; |
| } |
| .viewcode-button { |
| display: inline-block; |
| padding: 8px 16px; |
| border: 0; |
| margin: 0; |
| outline: 0; |
| border-radius: 2px; |
| -webkit-box-shadow: 0 3px 5px 0 rgba(0,0,0,.3); |
| box-shadow: 0 3px 6px 0 rgba(0,0,0,.3); |
| color: #404040; |
| background-color: #e7e7e7; |
| cursor: pointer; |
| font-size: 16px; |
| font-weight: 500; |
| line-height: 1; |
| text-decoration: none; |
| text-overflow: ellipsis; |
| overflow: hidden; |
| text-transform: uppercase; |
| -webkit-transition: background-color .2s; |
| transition: background-color .2s; |
| vertical-align: middle; |
| white-space: nowrap; |
| } |
| .viewcode-button:visited { |
| color: #404040; |
| } |
| .viewcode-button:hover, .viewcode-button:focus { |
| color: #404040; |
| background-color: #d6d6d6; |
| } |
| </style> |
| |
| </head> |
| |
| <body class="wy-body-for-nav"> |
| |
| |
| <div class="wy-grid-for-nav"> |
| |
| <nav data-toggle="wy-nav-shift" class="wy-nav-side"> |
| <div class="wy-side-scroll"> |
| <div class="wy-side-nav-search" > |
| |
| |
| |
| <a href="../../../../index.html" class="icon icon-home"> Airflow |
| |
| |
| |
| </a> |
| |
| |
| |
| |
| <div class="version"> |
| 1.10.3 |
| </div> |
| |
| |
| |
| |
| <div role="search"> |
| <form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get"> |
| <input type="text" name="q" placeholder="Search docs" /> |
| <input type="hidden" name="check_keywords" value="yes" /> |
| <input type="hidden" name="area" value="default" /> |
| </form> |
| </div> |
| |
| |
| </div> |
| |
| <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> |
| |
| |
| |
| |
| |
| |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../project.html">Project</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../license.html">License</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../start.html">Quick Start</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../installation.html">Installation</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../tutorial.html">Tutorial</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../howto/index.html">How-to Guides</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../ui.html">UI / Screenshots</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../concepts.html">Concepts</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../profiling.html">Data Profiling</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../cli.html">Command Line Interface</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling & Triggers</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../plugins.html">Plugins</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../security.html">Security</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../timezone.html">Time zones</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../api.html">Experimental Rest API</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../integration.html">Integration</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../metrics.html">Metrics</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../kubernetes.html">Kubernetes</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../lineage.html">Lineage</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../changelog.html">Changelog</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../faq.html">FAQ</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../macros.html">Macros reference</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../_api/index.html">API Reference</a></li> |
| </ul> |
| |
| |
| |
| </div> |
| </div> |
| </nav> |
| |
| <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> |
| |
| |
| <nav class="wy-nav-top" aria-label="top navigation"> |
| |
| <i data-toggle="wy-nav-top" class="fa fa-bars"></i> |
| <a href="../../../../index.html">Airflow</a> |
| |
| </nav> |
| |
| |
| <div class="wy-nav-content"> |
| |
| <div class="rst-content"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <div role="navigation" aria-label="breadcrumbs navigation"> |
| |
| <ul class="wy-breadcrumbs"> |
| |
| <li><a href="../../../../index.html">Docs</a> »</li> |
| |
| <li><a href="../../../index.html">Module code</a> »</li> |
| |
| <li><a href="../operators.html">airflow.contrib.operators</a> »</li> |
| |
| <li>airflow.contrib.operators.dataproc_operator</li> |
| |
| |
| <li class="wy-breadcrumbs-aside"> |
| |
| </li> |
| |
| </ul> |
| |
| |
| <hr/> |
| </div> |
| <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> |
| <div itemprop="articleBody"> |
| |
| <h1>Source code for airflow.contrib.operators.dataproc_operator</h1><div class="highlight"><pre> |
| <span></span><span class="c1"># -*- coding: utf-8 -*-</span> |
| <span class="c1">#</span> |
| <span class="c1"># Licensed to the Apache Software Foundation (ASF) under one</span> |
| <span class="c1"># or more contributor license agreements. See the NOTICE file</span> |
| <span class="c1"># distributed with this work for additional information</span> |
| <span class="c1"># regarding copyright ownership. The ASF licenses this file</span> |
| <span class="c1"># to you under the Apache License, Version 2.0 (the</span> |
| <span class="c1"># "License"); you may not use this file except in compliance</span> |
| <span class="c1"># with the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing,</span> |
| <span class="c1"># software distributed under the License is distributed on an</span> |
| <span class="c1"># "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span> |
| <span class="c1"># KIND, either express or implied. See the License for the</span> |
| <span class="c1"># specific language governing permissions and limitations</span> |
| <span class="c1"># under the License.</span> |
| <span class="c1">#</span> |
| |
| <span class="kn">import</span> <span class="nn">ntpath</span> |
| <span class="kn">import</span> <span class="nn">os</span> |
| <span class="kn">import</span> <span class="nn">re</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">datetime</span> <span class="k">import</span> <span class="n">timedelta</span> |
| |
| <span class="kn">from</span> <span class="nn">airflow.contrib.hooks.gcp_dataproc_hook</span> <span class="k">import</span> <span class="n">DataProcHook</span> |
| <span class="kn">from</span> <span class="nn">airflow.contrib.hooks.gcs_hook</span> <span class="k">import</span> <span class="n">GoogleCloudStorageHook</span> |
| <span class="kn">from</span> <span class="nn">airflow.exceptions</span> <span class="k">import</span> <span class="n">AirflowException</span> |
| <span class="kn">from</span> <span class="nn">airflow.models</span> <span class="k">import</span> <span class="n">BaseOperator</span> |
| <span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="k">import</span> <span class="n">apply_defaults</span> |
| <span class="kn">from</span> <span class="nn">airflow.version</span> <span class="k">import</span> <span class="n">version</span> |
| <span class="kn">from</span> <span class="nn">googleapiclient.errors</span> <span class="k">import</span> <span class="n">HttpError</span> |
| <span class="kn">from</span> <span class="nn">airflow.utils</span> <span class="k">import</span> <span class="n">timezone</span> |
| |
| |
| <div class="viewcode-block" id="DataprocClusterCreateOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocClusterCreateOperator">[docs]</a><span class="k">class</span> <span class="nc">DataprocClusterCreateOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Create a new cluster on Google Cloud Dataproc. The operator will wait until the</span> |
| <span class="sd"> creation is successful or an error occurs in the creation process.</span> |
| |
| <span class="sd"> The parameters allow to configure the cluster. Please refer to</span> |
| |
| <span class="sd"> https://cloud.google.com/dataproc/docs/reference/rest/v1/projects.regions.clusters</span> |
| |
| <span class="sd"> for a detailed explanation on the different parameters. Most of the configuration</span> |
| <span class="sd"> parameters detailed in the link are available as a parameter to this operator.</span> |
| |
| <span class="sd"> :param cluster_name: The name of the DataProc cluster to create. (templated)</span> |
| <span class="sd"> :type cluster_name: str</span> |
| <span class="sd"> :param project_id: The ID of the google cloud project in which</span> |
| <span class="sd"> to create the cluster. (templated)</span> |
| <span class="sd"> :type project_id: str</span> |
| <span class="sd"> :param num_workers: The # of workers to spin up. If set to zero will</span> |
| <span class="sd"> spin up cluster in a single node mode</span> |
| <span class="sd"> :type num_workers: int</span> |
| <span class="sd"> :param storage_bucket: The storage bucket to use, setting to None lets dataproc</span> |
| <span class="sd"> generate a custom one for you</span> |
| <span class="sd"> :type storage_bucket: str</span> |
| <span class="sd"> :param init_actions_uris: List of GCS uri's containing</span> |
| <span class="sd"> dataproc initialization scripts</span> |
| <span class="sd"> :type init_actions_uris: list[str]</span> |
| <span class="sd"> :param init_action_timeout: Amount of time executable scripts in</span> |
| <span class="sd"> init_actions_uris has to complete</span> |
| <span class="sd"> :type init_action_timeout: str</span> |
| <span class="sd"> :param metadata: dict of key-value google compute engine metadata entries</span> |
| <span class="sd"> to add to all instances</span> |
| <span class="sd"> :type metadata: dict</span> |
| <span class="sd"> :param image_version: the version of software inside the Dataproc cluster</span> |
| <span class="sd"> :type image_version: str</span> |
| <span class="sd"> :param custom_image: custom Dataproc image for more info see</span> |
| <span class="sd"> https://cloud.google.com/dataproc/docs/guides/dataproc-images</span> |
| <span class="sd"> :type: custom_image: str</span> |
| <span class="sd"> :param properties: dict of properties to set on</span> |
| <span class="sd"> config files (e.g. spark-defaults.conf), see</span> |
| <span class="sd"> https://cloud.google.com/dataproc/docs/reference/rest/v1/projects.regions.clusters#SoftwareConfig</span> |
| <span class="sd"> :type properties: dict</span> |
| <span class="sd"> :param master_machine_type: Compute engine machine type to use for the master node</span> |
| <span class="sd"> :type master_machine_type: str</span> |
| <span class="sd"> :param master_disk_type: Type of the boot disk for the master node</span> |
| <span class="sd"> (default is ``pd-standard``).</span> |
| <span class="sd"> Valid values: ``pd-ssd`` (Persistent Disk Solid State Drive) or</span> |
| <span class="sd"> ``pd-standard`` (Persistent Disk Hard Disk Drive).</span> |
| <span class="sd"> :type master_disk_type: str</span> |
| <span class="sd"> :param master_disk_size: Disk size for the master node</span> |
| <span class="sd"> :type master_disk_size: int</span> |
| <span class="sd"> :param worker_machine_type: Compute engine machine type to use for the worker nodes</span> |
| <span class="sd"> :type worker_machine_type: str</span> |
| <span class="sd"> :param worker_disk_type: Type of the boot disk for the worker node</span> |
| <span class="sd"> (default is ``pd-standard``).</span> |
| <span class="sd"> Valid values: ``pd-ssd`` (Persistent Disk Solid State Drive) or</span> |
| <span class="sd"> ``pd-standard`` (Persistent Disk Hard Disk Drive).</span> |
| <span class="sd"> :type worker_disk_type: str</span> |
| <span class="sd"> :param worker_disk_size: Disk size for the worker nodes</span> |
| <span class="sd"> :type worker_disk_size: int</span> |
| <span class="sd"> :param num_preemptible_workers: The # of preemptible worker nodes to spin up</span> |
| <span class="sd"> :type num_preemptible_workers: int</span> |
| <span class="sd"> :param labels: dict of labels to add to the cluster</span> |
| <span class="sd"> :type labels: dict</span> |
| <span class="sd"> :param zone: The zone where the cluster will be located. (templated)</span> |
| <span class="sd"> :type zone: str</span> |
| <span class="sd"> :param network_uri: The network uri to be used for machine communication, cannot be</span> |
| <span class="sd"> specified with subnetwork_uri</span> |
| <span class="sd"> :type network_uri: str</span> |
| <span class="sd"> :param subnetwork_uri: The subnetwork uri to be used for machine communication,</span> |
| <span class="sd"> cannot be specified with network_uri</span> |
| <span class="sd"> :type subnetwork_uri: str</span> |
| <span class="sd"> :param internal_ip_only: If true, all instances in the cluster will only</span> |
| <span class="sd"> have internal IP addresses. This can only be enabled for subnetwork</span> |
| <span class="sd"> enabled networks</span> |
| <span class="sd"> :type internal_ip_only: bool</span> |
| <span class="sd"> :param tags: The GCE tags to add to all instances</span> |
| <span class="sd"> :type tags: list[str]</span> |
| <span class="sd"> :param region: leave as 'global', might become relevant in the future. (templated)</span> |
| <span class="sd"> :type region: str</span> |
| <span class="sd"> :param gcp_conn_id: The connection ID to use connecting to Google Cloud Platform.</span> |
| <span class="sd"> :type gcp_conn_id: str</span> |
| <span class="sd"> :param delegate_to: The account to impersonate, if any.</span> |
| <span class="sd"> For this to work, the service account making the request must have domain-wide</span> |
| <span class="sd"> delegation enabled.</span> |
| <span class="sd"> :type delegate_to: str</span> |
| <span class="sd"> :param service_account: The service account of the dataproc instances.</span> |
| <span class="sd"> :type service_account: str</span> |
| <span class="sd"> :param service_account_scopes: The URIs of service account scopes to be included.</span> |
| <span class="sd"> :type service_account_scopes: list[str]</span> |
| <span class="sd"> :param idle_delete_ttl: The longest duration that cluster would keep alive while</span> |
| <span class="sd"> staying idle. Passing this threshold will cause cluster to be auto-deleted.</span> |
| <span class="sd"> A duration in seconds.</span> |
| <span class="sd"> :type idle_delete_ttl: int</span> |
| <span class="sd"> :param auto_delete_time: The time when cluster will be auto-deleted.</span> |
| <span class="sd"> :type auto_delete_time: datetime.datetime</span> |
| <span class="sd"> :param auto_delete_ttl: The life duration of cluster, the cluster will be</span> |
| <span class="sd"> auto-deleted at the end of this duration.</span> |
| <span class="sd"> A duration in seconds. (If auto_delete_time is set this parameter will be ignored)</span> |
| <span class="sd"> :type auto_delete_ttl: int</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="DataprocClusterCreateOperator.template_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocClusterCreateOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'cluster_name'</span><span class="p">,</span> <span class="s1">'project_id'</span><span class="p">,</span> <span class="s1">'zone'</span><span class="p">,</span> <span class="s1">'region'</span><span class="p">]</span></div> |
| |
| <span class="nd">@apply_defaults</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> |
| <span class="n">cluster_name</span><span class="p">,</span> |
| <span class="n">project_id</span><span class="p">,</span> |
| <span class="n">num_workers</span><span class="p">,</span> |
| <span class="n">zone</span><span class="p">,</span> |
| <span class="n">network_uri</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">subnetwork_uri</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">internal_ip_only</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">tags</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">storage_bucket</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">init_actions_uris</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">init_action_timeout</span><span class="o">=</span><span class="s2">"10m"</span><span class="p">,</span> |
| <span class="n">metadata</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">custom_image</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">image_version</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">properties</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">master_machine_type</span><span class="o">=</span><span class="s1">'n1-standard-4'</span><span class="p">,</span> |
| <span class="n">master_disk_type</span><span class="o">=</span><span class="s1">'pd-standard'</span><span class="p">,</span> |
| <span class="n">master_disk_size</span><span class="o">=</span><span class="mi">500</span><span class="p">,</span> |
| <span class="n">worker_machine_type</span><span class="o">=</span><span class="s1">'n1-standard-4'</span><span class="p">,</span> |
| <span class="n">worker_disk_type</span><span class="o">=</span><span class="s1">'pd-standard'</span><span class="p">,</span> |
| <span class="n">worker_disk_size</span><span class="o">=</span><span class="mi">500</span><span class="p">,</span> |
| <span class="n">num_preemptible_workers</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> |
| <span class="n">labels</span><span class="o">=</span><span class="kc">None</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">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">service_account</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">service_account_scopes</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">idle_delete_ttl</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">auto_delete_time</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">auto_delete_ttl</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="o">*</span><span class="n">args</span><span class="p">,</span> |
| <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| |
| <span class="nb">super</span><span class="p">(</span><span class="n">DataprocClusterCreateOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span> <span class="o">=</span> <span class="n">gcp_conn_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span> <span class="o">=</span> <span class="n">delegate_to</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span> <span class="o">=</span> <span class="n">cluster_name</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">num_workers</span> <span class="o">=</span> <span class="n">num_workers</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">num_preemptible_workers</span> <span class="o">=</span> <span class="n">num_preemptible_workers</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">storage_bucket</span> <span class="o">=</span> <span class="n">storage_bucket</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">init_actions_uris</span> <span class="o">=</span> <span class="n">init_actions_uris</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">init_action_timeout</span> <span class="o">=</span> <span class="n">init_action_timeout</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">metadata</span> <span class="o">=</span> <span class="n">metadata</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">custom_image</span> <span class="o">=</span> <span class="n">custom_image</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">image_version</span> <span class="o">=</span> <span class="n">image_version</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">properties</span> <span class="o">=</span> <span class="n">properties</span> <span class="ow">or</span> <span class="nb">dict</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">master_machine_type</span> <span class="o">=</span> <span class="n">master_machine_type</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">master_disk_type</span> <span class="o">=</span> <span class="n">master_disk_type</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">master_disk_size</span> <span class="o">=</span> <span class="n">master_disk_size</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">worker_machine_type</span> <span class="o">=</span> <span class="n">worker_machine_type</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">worker_disk_type</span> <span class="o">=</span> <span class="n">worker_disk_type</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">worker_disk_size</span> <span class="o">=</span> <span class="n">worker_disk_size</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">labels</span> <span class="o">=</span> <span class="n">labels</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">zone</span> <span class="o">=</span> <span class="n">zone</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">network_uri</span> <span class="o">=</span> <span class="n">network_uri</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">subnetwork_uri</span> <span class="o">=</span> <span class="n">subnetwork_uri</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">internal_ip_only</span> <span class="o">=</span> <span class="n">internal_ip_only</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">tags</span> <span class="o">=</span> <span class="n">tags</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">service_account</span> <span class="o">=</span> <span class="n">service_account</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">service_account_scopes</span> <span class="o">=</span> <span class="n">service_account_scopes</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">idle_delete_ttl</span> <span class="o">=</span> <span class="n">idle_delete_ttl</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">auto_delete_time</span> <span class="o">=</span> <span class="n">auto_delete_time</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">auto_delete_ttl</span> <span class="o">=</span> <span class="n">auto_delete_ttl</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">single_node</span> <span class="o">=</span> <span class="n">num_workers</span> <span class="o">==</span> <span class="mi">0</span> |
| |
| <span class="k">assert</span> <span class="ow">not</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">custom_image</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">image_version</span><span class="p">),</span> \ |
| <span class="s2">"custom_image and image_version can't be both set"</span> |
| |
| <span class="k">assert</span> <span class="p">(</span> |
| <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">single_node</span> <span class="ow">or</span> <span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">single_node</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_preemptible_workers</span> <span class="o">==</span> <span class="mi">0</span> |
| <span class="p">)</span> |
| <span class="p">),</span> <span class="s2">"num_workers == 0 means single node mode - no preemptibles allowed"</span> |
| |
| <span class="k">assert</span> <span class="ow">not</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">custom_image</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">image_version</span><span class="p">),</span> \ |
| <span class="s2">"custom_image and image_version can't be both set"</span> |
| |
| <div class="viewcode-block" id="DataprocClusterCreateOperator._get_cluster_list_for_project"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocClusterCreateOperator._get_cluster_list_for_project">[docs]</a> <span class="k">def</span> <span class="nf">_get_cluster_list_for_project</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">service</span><span class="p">):</span> |
| <span class="n">result</span> <span class="o">=</span> <span class="n">service</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">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">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="o">.</span><span class="n">execute</span><span class="p">()</span> |
| <span class="k">return</span> <span class="n">result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'clusters'</span><span class="p">,</span> <span class="p">[])</span></div> |
| |
| <div class="viewcode-block" id="DataprocClusterCreateOperator._get_cluster"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocClusterCreateOperator._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">service</span><span class="p">):</span> |
| <span class="n">cluster_list</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_cluster_list_for_project</span><span class="p">(</span><span class="n">service</span><span class="p">)</span> |
| <span class="n">cluster</span> <span class="o">=</span> <span class="p">[</span><span class="n">c</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">cluster_list</span> <span class="k">if</span> <span class="n">c</span><span class="p">[</span><span class="s1">'clusterName'</span><span class="p">]</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">]</span> |
| <span class="k">if</span> <span class="n">cluster</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">cluster</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="k">return</span> <span class="kc">None</span></div> |
| |
| <div class="viewcode-block" id="DataprocClusterCreateOperator._get_cluster_state"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocClusterCreateOperator._get_cluster_state">[docs]</a> <span class="k">def</span> <span class="nf">_get_cluster_state</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">service</span><span class="p">):</span> |
| <span class="n">cluster</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_cluster</span><span class="p">(</span><span class="n">service</span><span class="p">)</span> |
| <span class="k">if</span> <span class="s1">'status'</span> <span class="ow">in</span> <span class="n">cluster</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">cluster</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">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="kc">None</span></div> |
| |
| <div class="viewcode-block" id="DataprocClusterCreateOperator._cluster_ready"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocClusterCreateOperator._cluster_ready">[docs]</a> <span class="k">def</span> <span class="nf">_cluster_ready</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">state</span><span class="p">,</span> <span class="n">service</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">state</span> <span class="o">==</span> <span class="s1">'RUNNING'</span><span class="p">:</span> |
| <span class="k">return</span> <span class="kc">True</span> |
| <span class="k">if</span> <span class="n">state</span> <span class="o">==</span> <span class="s1">'ERROR'</span><span class="p">:</span> |
| <span class="n">cluster</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_cluster</span><span class="p">(</span><span class="n">service</span><span class="p">)</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">error_details</span> <span class="o">=</span> <span class="n">cluster</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">except</span> <span class="ne">KeyError</span><span class="p">:</span> |
| <span class="n">error_details</span> <span class="o">=</span> <span class="s1">'Unknown error in cluster creation, '</span> \ |
| <span class="s1">'check Google Cloud console for details.'</span> |
| <span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span><span class="n">error_details</span><span class="p">)</span> |
| <span class="k">return</span> <span class="kc">False</span></div> |
| |
| <div class="viewcode-block" id="DataprocClusterCreateOperator._wait_for_done"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocClusterCreateOperator._wait_for_done">[docs]</a> <span class="k">def</span> <span class="nf">_wait_for_done</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">service</span><span class="p">):</span> |
| <span class="k">while</span> <span class="kc">True</span><span class="p">:</span> |
| <span class="n">state</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_cluster_state</span><span class="p">(</span><span class="n">service</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">state</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"No state for cluster '</span><span class="si">%s</span><span class="s2">'"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">)</span> |
| <span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="mi">15</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"State for cluster '</span><span class="si">%s</span><span class="s2">' is </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">,</span> <span class="n">state</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cluster_ready</span><span class="p">(</span><span class="n">state</span><span class="p">,</span> <span class="n">service</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span> |
| <span class="s2">"Cluster '</span><span class="si">%s</span><span class="s2">' successfully created"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span> |
| <span class="p">)</span> |
| <span class="k">return</span> |
| <span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="mi">15</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="DataprocClusterCreateOperator._get_init_action_timeout"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocClusterCreateOperator._get_init_action_timeout">[docs]</a> <span class="k">def</span> <span class="nf">_get_init_action_timeout</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="n">match</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">match</span><span class="p">(</span><span class="sa">r</span><span class="s2">"^(\d+)(s|m)$"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">init_action_timeout</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">match</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">match</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span> <span class="o">==</span> <span class="s2">"s"</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">init_action_timeout</span> |
| <span class="k">elif</span> <span class="n">match</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span> <span class="o">==</span> <span class="s2">"m"</span><span class="p">:</span> |
| <span class="n">val</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">match</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">1</span><span class="p">))</span> |
| <span class="k">return</span> <span class="s2">"</span><span class="si">{}</span><span class="s2">s"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">timedelta</span><span class="p">(</span><span class="n">minutes</span><span class="o">=</span><span class="n">val</span><span class="p">)</span><span class="o">.</span><span class="n">seconds</span><span class="p">)</span> |
| |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span> |
| <span class="s2">"DataprocClusterCreateOperator init_action_timeout"</span></div> |
| <span class="s2">" should be expressed in minutes or seconds. i.e. 10m, 30s"</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="DataprocClusterCreateOperator._build_cluster_data"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocClusterCreateOperator._build_cluster_data">[docs]</a> <span class="k">def</span> <span class="nf">_build_cluster_data</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="n">zone_uri</span> <span class="o">=</span> \ |
| <span class="s1">'https://www.googleapis.com/compute/v1/projects/</span><span class="si">{}</span><span class="s1">/zones/</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">project_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">zone</span> |
| <span class="p">)</span> |
| <span class="n">master_type_uri</span> <span class="o">=</span> \ |
| <span class="s2">"https://www.googleapis.com/compute/v1/projects/</span><span class="si">{}</span><span class="s2">/zones/</span><span class="si">{}</span><span class="s2">/machineTypes/</span><span class="si">{}</span><span class="s2">"</span>\ |
| <span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">project_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">zone</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">master_machine_type</span><span class="p">)</span> |
| <span class="n">worker_type_uri</span> <span class="o">=</span> \ |
| <span class="s2">"https://www.googleapis.com/compute/v1/projects/</span><span class="si">{}</span><span class="s2">/zones/</span><span class="si">{}</span><span class="s2">/machineTypes/</span><span class="si">{}</span><span class="s2">"</span>\ |
| <span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">project_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">zone</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">worker_machine_type</span><span class="p">)</span> |
| |
| <span class="n">cluster_data</span> <span class="o">=</span> <span class="p">{</span> |
| <span class="s1">'projectId'</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="s1">'clusterName'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">,</span> |
| <span class="s1">'config'</span><span class="p">:</span> <span class="p">{</span> |
| <span class="s1">'gceClusterConfig'</span><span class="p">:</span> <span class="p">{</span> |
| <span class="s1">'zoneUri'</span><span class="p">:</span> <span class="n">zone_uri</span> |
| <span class="p">},</span> |
| <span class="s1">'masterConfig'</span><span class="p">:</span> <span class="p">{</span> |
| <span class="s1">'numInstances'</span><span class="p">:</span> <span class="mi">1</span><span class="p">,</span> |
| <span class="s1">'machineTypeUri'</span><span class="p">:</span> <span class="n">master_type_uri</span><span class="p">,</span> |
| <span class="s1">'diskConfig'</span><span class="p">:</span> <span class="p">{</span> |
| <span class="s1">'bootDiskType'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">master_disk_type</span><span class="p">,</span> |
| <span class="s1">'bootDiskSizeGb'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">master_disk_size</span> |
| <span class="p">}</span> |
| <span class="p">},</span> |
| <span class="s1">'workerConfig'</span><span class="p">:</span> <span class="p">{</span> |
| <span class="s1">'numInstances'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_workers</span><span class="p">,</span> |
| <span class="s1">'machineTypeUri'</span><span class="p">:</span> <span class="n">worker_type_uri</span><span class="p">,</span> |
| <span class="s1">'diskConfig'</span><span class="p">:</span> <span class="p">{</span> |
| <span class="s1">'bootDiskType'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">worker_disk_type</span><span class="p">,</span> |
| <span class="s1">'bootDiskSizeGb'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">worker_disk_size</span> |
| <span class="p">}</span> |
| <span class="p">},</span> |
| <span class="s1">'secondaryWorkerConfig'</span><span class="p">:</span> <span class="p">{},</span> |
| <span class="s1">'softwareConfig'</span><span class="p">:</span> <span class="p">{},</span> |
| <span class="s1">'lifecycleConfig'</span><span class="p">:</span> <span class="p">{}</span> |
| <span class="p">}</span> |
| <span class="p">}</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_preemptible_workers</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span> |
| <span class="n">cluster_data</span><span class="p">[</span><span class="s1">'config'</span><span class="p">][</span><span class="s1">'secondaryWorkerConfig'</span><span class="p">]</span> <span class="o">=</span> <span class="p">{</span> |
| <span class="s1">'numInstances'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_preemptible_workers</span><span class="p">,</span> |
| <span class="s1">'machineTypeUri'</span><span class="p">:</span> <span class="n">worker_type_uri</span><span class="p">,</span> |
| <span class="s1">'diskConfig'</span><span class="p">:</span> <span class="p">{</span> |
| <span class="s1">'bootDiskType'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">worker_disk_type</span><span class="p">,</span> |
| <span class="s1">'bootDiskSizeGb'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">worker_disk_size</span> |
| <span class="p">},</span> |
| <span class="s1">'isPreemptible'</span><span class="p">:</span> <span class="kc">True</span> |
| <span class="p">}</span> |
| |
| <span class="n">cluster_data</span><span class="p">[</span><span class="s1">'labels'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">labels</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">labels</span> <span class="k">else</span> <span class="p">{}</span> |
| <span class="c1"># Dataproc labels must conform to the following regex:</span> |
| <span class="c1"># [a-z]([-a-z0-9]*[a-z0-9])? (current airflow version string follows</span> |
| <span class="c1"># semantic versioning spec: x.y.z).</span> |
| <span class="n">cluster_data</span><span class="p">[</span><span class="s1">'labels'</span><span class="p">]</span><span class="o">.</span><span class="n">update</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="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">storage_bucket</span><span class="p">:</span> |
| <span class="n">cluster_data</span><span class="p">[</span><span class="s1">'config'</span><span class="p">][</span><span class="s1">'configBucket'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">storage_bucket</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">metadata</span><span class="p">:</span> |
| <span class="n">cluster_data</span><span class="p">[</span><span class="s1">'config'</span><span class="p">][</span><span class="s1">'gceClusterConfig'</span><span class="p">][</span><span class="s1">'metadata'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">metadata</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">network_uri</span><span class="p">:</span> |
| <span class="n">cluster_data</span><span class="p">[</span><span class="s1">'config'</span><span class="p">][</span><span class="s1">'gceClusterConfig'</span><span class="p">][</span><span class="s1">'networkUri'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">network_uri</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">subnetwork_uri</span><span class="p">:</span> |
| <span class="n">cluster_data</span><span class="p">[</span><span class="s1">'config'</span><span class="p">][</span><span class="s1">'gceClusterConfig'</span><span class="p">][</span><span class="s1">'subnetworkUri'</span><span class="p">]</span> <span class="o">=</span> \ |
| <span class="bp">self</span><span class="o">.</span><span class="n">subnetwork_uri</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">internal_ip_only</span><span class="p">:</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">subnetwork_uri</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s2">"Set internal_ip_only to true only when"</span> |
| <span class="s2">" you pass a subnetwork_uri."</span><span class="p">)</span> |
| <span class="n">cluster_data</span><span class="p">[</span><span class="s1">'config'</span><span class="p">][</span><span class="s1">'gceClusterConfig'</span><span class="p">][</span><span class="s1">'internalIpOnly'</span><span class="p">]</span> <span class="o">=</span> <span class="kc">True</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">tags</span><span class="p">:</span> |
| <span class="n">cluster_data</span><span class="p">[</span><span class="s1">'config'</span><span class="p">][</span><span class="s1">'gceClusterConfig'</span><span class="p">][</span><span class="s1">'tags'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">tags</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">image_version</span><span class="p">:</span> |
| <span class="n">cluster_data</span><span class="p">[</span><span class="s1">'config'</span><span class="p">][</span><span class="s1">'softwareConfig'</span><span class="p">][</span><span class="s1">'imageVersion'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">image_version</span> |
| <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">custom_image</span><span class="p">:</span> |
| <span class="n">custom_image_url</span> <span class="o">=</span> <span class="s1">'https://www.googleapis.com/compute/beta/projects/'</span> \ |
| <span class="s1">'</span><span class="si">{}</span><span class="s1">/global/images/</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">project_id</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">custom_image</span><span class="p">)</span> |
| <span class="n">cluster_data</span><span class="p">[</span><span class="s1">'config'</span><span class="p">][</span><span class="s1">'masterConfig'</span><span class="p">][</span><span class="s1">'imageUri'</span><span class="p">]</span> <span class="o">=</span> <span class="n">custom_image_url</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">single_node</span><span class="p">:</span> |
| <span class="n">cluster_data</span><span class="p">[</span><span class="s1">'config'</span><span class="p">][</span><span class="s1">'workerConfig'</span><span class="p">][</span><span class="s1">'imageUri'</span><span class="p">]</span> <span class="o">=</span> <span class="n">custom_image_url</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">single_node</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">properties</span><span class="p">[</span><span class="s2">"dataproc:dataproc.allow.zero.workers"</span><span class="p">]</span> <span class="o">=</span> <span class="s2">"true"</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">properties</span><span class="p">:</span> |
| <span class="n">cluster_data</span><span class="p">[</span><span class="s1">'config'</span><span class="p">][</span><span class="s1">'softwareConfig'</span><span class="p">][</span><span class="s1">'properties'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">properties</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">idle_delete_ttl</span><span class="p">:</span> |
| <span class="n">cluster_data</span><span class="p">[</span><span class="s1">'config'</span><span class="p">][</span><span class="s1">'lifecycleConfig'</span><span class="p">][</span><span class="s1">'idleDeleteTtl'</span><span class="p">]</span> <span class="o">=</span> \ |
| <span class="s2">"</span><span class="si">{}</span><span class="s2">s"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">idle_delete_ttl</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">auto_delete_time</span><span class="p">:</span> |
| <span class="n">utc_auto_delete_time</span> <span class="o">=</span> <span class="n">timezone</span><span class="o">.</span><span class="n">convert_to_utc</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">auto_delete_time</span><span class="p">)</span> |
| <span class="n">cluster_data</span><span class="p">[</span><span class="s1">'config'</span><span class="p">][</span><span class="s1">'lifecycleConfig'</span><span class="p">][</span><span class="s1">'autoDeleteTime'</span><span class="p">]</span> <span class="o">=</span> \ |
| <span class="n">utc_auto_delete_time</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="s1">'%Y-%m-</span><span class="si">%d</span><span class="s1">T%H:%M:%S.</span><span class="si">%f</span><span class="s1">Z'</span><span class="p">,</span> <span class="n">formatter</span><span class="o">=</span><span class="s1">'classic'</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">auto_delete_ttl</span><span class="p">:</span> |
| <span class="n">cluster_data</span><span class="p">[</span><span class="s1">'config'</span><span class="p">][</span><span class="s1">'lifecycleConfig'</span><span class="p">][</span><span class="s1">'autoDeleteTtl'</span><span class="p">]</span> <span class="o">=</span> \ |
| <span class="s2">"</span><span class="si">{}</span><span class="s2">s"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">auto_delete_ttl</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">init_actions_uris</span><span class="p">:</span> |
| <span class="n">init_actions_dict</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="p">{</span> |
| <span class="s1">'executableFile'</span><span class="p">:</span> <span class="n">uri</span><span class="p">,</span> |
| <span class="s1">'executionTimeout'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_init_action_timeout</span><span class="p">()</span> |
| <span class="p">}</span> <span class="k">for</span> <span class="n">uri</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">init_actions_uris</span> |
| <span class="p">]</span> |
| <span class="n">cluster_data</span><span class="p">[</span><span class="s1">'config'</span><span class="p">][</span><span class="s1">'initializationActions'</span><span class="p">]</span> <span class="o">=</span> <span class="n">init_actions_dict</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">service_account</span><span class="p">:</span> |
| <span class="n">cluster_data</span><span class="p">[</span><span class="s1">'config'</span><span class="p">][</span><span class="s1">'gceClusterConfig'</span><span class="p">][</span><span class="s1">'serviceAccount'</span><span class="p">]</span> <span class="o">=</span>\ |
| <span class="bp">self</span><span class="o">.</span><span class="n">service_account</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">service_account_scopes</span><span class="p">:</span> |
| <span class="n">cluster_data</span><span class="p">[</span><span class="s1">'config'</span><span class="p">][</span><span class="s1">'gceClusterConfig'</span><span class="p">][</span><span class="s1">'serviceAccountScopes'</span><span class="p">]</span> <span class="o">=</span>\ |
| <span class="bp">self</span><span class="o">.</span><span class="n">service_account_scopes</span> |
| <span class="k">return</span> <span class="n">cluster_data</span></div> |
| |
| <div class="viewcode-block" id="DataprocClusterCreateOperator.execute"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocClusterCreateOperator.execute">[docs]</a> <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Creating cluster: </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">cluster_name</span><span class="p">)</span> |
| <span class="n">hook</span> <span class="o">=</span> <span class="n">DataProcHook</span><span class="p">(</span> |
| <span class="n">gcp_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span><span class="p">,</span> |
| <span class="n">delegate_to</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span> |
| <span class="p">)</span> |
| <span class="n">service</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_cluster</span><span class="p">(</span><span class="n">service</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">'Cluster </span><span class="si">%s</span><span class="s1"> already exists... Checking status...'</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span> |
| <span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_wait_for_done</span><span class="p">(</span><span class="n">service</span><span class="p">)</span> |
| <span class="k">return</span> <span class="kc">True</span> |
| |
| <span class="n">cluster_data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_build_cluster_data</span><span class="p">()</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">service</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">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">create</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">cluster_data</span> |
| <span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">()</span> |
| <span class="k">except</span> <span class="n">HttpError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> |
| <span class="c1"># probably two cluster start commands at the same time</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="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_cluster</span><span class="p">(</span><span class="n">service</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">'Cluster </span><span class="si">{}</span><span class="s1"> already exists... Checking status...'</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span> |
| <span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_wait_for_done</span><span class="p">(</span><span class="n">service</span><span class="p">)</span> |
| <span class="k">return</span> <span class="kc">True</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">e</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_wait_for_done</span><span class="p">(</span><span class="n">service</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="DataprocClusterScaleOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocClusterScaleOperator">[docs]</a><span class="k">class</span> <span class="nc">DataprocClusterScaleOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Scale, up or down, a cluster on Google Cloud Dataproc.</span> |
| <span class="sd"> The operator will wait until the cluster is re-scaled.</span> |
| |
| <span class="sd"> **Example**: ::</span> |
| |
| <span class="sd"> t1 = DataprocClusterScaleOperator(</span> |
| <span class="sd"> task_id='dataproc_scale',</span> |
| <span class="sd"> project_id='my-project',</span> |
| <span class="sd"> cluster_name='cluster-1',</span> |
| <span class="sd"> num_workers=10,</span> |
| <span class="sd"> num_preemptible_workers=10,</span> |
| <span class="sd"> graceful_decommission_timeout='1h',</span> |
| <span class="sd"> dag=dag)</span> |
| |
| <span class="sd"> .. seealso::</span> |
| <span class="sd"> For more detail on about scaling clusters have a look at the reference:</span> |
| <span class="sd"> https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/scaling-clusters</span> |
| |
| <span class="sd"> :param cluster_name: The name of the cluster to scale. (templated)</span> |
| <span class="sd"> :type cluster_name: str</span> |
| <span class="sd"> :param project_id: The ID of the google cloud project in which</span> |
| <span class="sd"> the cluster runs. (templated)</span> |
| <span class="sd"> :type project_id: str</span> |
| <span class="sd"> :param region: The region for the dataproc cluster. (templated)</span> |
| <span class="sd"> :type region: str</span> |
| <span class="sd"> :param gcp_conn_id: The connection ID to use connecting to Google Cloud Platform.</span> |
| <span class="sd"> :type gcp_conn_id: str</span> |
| <span class="sd"> :param num_workers: The new number of workers</span> |
| <span class="sd"> :type num_workers: int</span> |
| <span class="sd"> :param num_preemptible_workers: The new number of preemptible workers</span> |
| <span class="sd"> :type num_preemptible_workers: int</span> |
| <span class="sd"> :param graceful_decommission_timeout: Timeout for graceful YARN decomissioning.</span> |
| <span class="sd"> Maximum value is 1d</span> |
| <span class="sd"> :type graceful_decommission_timeout: str</span> |
| <span class="sd"> :param delegate_to: The account to impersonate, if any.</span> |
| <span class="sd"> For this to work, the service account making the request must have domain-wide</span> |
| <span class="sd"> delegation enabled.</span> |
| <span class="sd"> :type delegate_to: str</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="DataprocClusterScaleOperator.template_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocClusterScaleOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'cluster_name'</span><span class="p">,</span> <span class="s1">'project_id'</span><span class="p">,</span> <span class="s1">'region'</span><span class="p">]</span></div> |
| |
| <span class="nd">@apply_defaults</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> |
| <span class="n">cluster_name</span><span class="p">,</span> |
| <span class="n">project_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="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">num_workers</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> |
| <span class="n">num_preemptible_workers</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> |
| <span class="n">graceful_decommission_timeout</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="o">*</span><span class="n">args</span><span class="p">,</span> |
| <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">DataprocClusterScaleOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span> <span class="o">=</span> <span class="n">gcp_conn_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span> <span class="o">=</span> <span class="n">delegate_to</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span> <span class="o">=</span> <span class="n">cluster_name</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_workers</span> <span class="o">=</span> <span class="n">num_workers</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">num_preemptible_workers</span> <span class="o">=</span> <span class="n">num_preemptible_workers</span> |
| |
| <span class="c1"># Optional</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">optional_arguments</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">if</span> <span class="n">graceful_decommission_timeout</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">optional_arguments</span><span class="p">[</span><span class="s1">'gracefulDecommissionTimeout'</span><span class="p">]</span> <span class="o">=</span> \ |
| <span class="bp">self</span><span class="o">.</span><span class="n">_get_graceful_decommission_timeout</span><span class="p">(</span> |
| <span class="n">graceful_decommission_timeout</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="DataprocClusterScaleOperator._wait_for_done"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocClusterScaleOperator._wait_for_done">[docs]</a> <span class="k">def</span> <span class="nf">_wait_for_done</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">service</span><span class="p">,</span> <span class="n">operation_name</span><span class="p">):</span> |
| <span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="mi">15</span><span class="p">)</span> |
| <span class="k">while</span> <span class="kc">True</span><span class="p">:</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">response</span> <span class="o">=</span> <span class="n">service</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">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="n">operation_name</span> |
| <span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">()</span> |
| |
| <span class="k">if</span> <span class="s1">'done'</span> <span class="ow">in</span> <span class="n">response</span> <span class="ow">and</span> <span class="n">response</span><span class="p">[</span><span class="s1">'done'</span><span class="p">]:</span> |
| <span class="k">if</span> <span class="s1">'error'</span> <span class="ow">in</span> <span class="n">response</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">response</span><span class="p">[</span><span class="s1">'error'</span><span class="p">]))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> |
| <span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="mi">15</span><span class="p">)</span> |
| <span class="k">except</span> <span class="n">HttpError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="s2">"Operation not found."</span><span class="p">)</span> |
| <span class="k">raise</span> <span class="n">e</span></div> |
| |
| <div class="viewcode-block" id="DataprocClusterScaleOperator._build_scale_cluster_data"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocClusterScaleOperator._build_scale_cluster_data">[docs]</a> <span class="k">def</span> <span class="nf">_build_scale_cluster_data</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="n">scale_data</span> <span class="o">=</span> <span class="p">{</span> |
| <span class="s1">'config'</span><span class="p">:</span> <span class="p">{</span> |
| <span class="s1">'workerConfig'</span><span class="p">:</span> <span class="p">{</span> |
| <span class="s1">'numInstances'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_workers</span> |
| <span class="p">},</span> |
| <span class="s1">'secondaryWorkerConfig'</span><span class="p">:</span> <span class="p">{</span> |
| <span class="s1">'numInstances'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_preemptible_workers</span> |
| <span class="p">}</span> |
| <span class="p">}</span> |
| <span class="p">}</span> |
| <span class="k">return</span> <span class="n">scale_data</span></div> |
| |
| <span class="nd">@staticmethod</span> |
| <div class="viewcode-block" id="DataprocClusterScaleOperator._get_graceful_decommission_timeout"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocClusterScaleOperator._get_graceful_decommission_timeout">[docs]</a> <span class="k">def</span> <span class="nf">_get_graceful_decommission_timeout</span><span class="p">(</span><span class="n">timeout</span><span class="p">):</span> |
| <span class="n">match</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">match</span><span class="p">(</span><span class="sa">r</span><span class="s2">"^(\d+)(s|m|h|d)$"</span><span class="p">,</span> <span class="n">timeout</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">match</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">match</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span> <span class="o">==</span> <span class="s2">"s"</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">timeout</span> |
| <span class="k">elif</span> <span class="n">match</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span> <span class="o">==</span> <span class="s2">"m"</span><span class="p">:</span> |
| <span class="n">val</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">match</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">1</span><span class="p">))</span> |
| <span class="k">return</span> <span class="s2">"</span><span class="si">{}</span><span class="s2">s"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">timedelta</span><span class="p">(</span><span class="n">minutes</span><span class="o">=</span><span class="n">val</span><span class="p">)</span><span class="o">.</span><span class="n">seconds</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">match</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span> <span class="o">==</span> <span class="s2">"h"</span><span class="p">:</span> |
| <span class="n">val</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">match</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">1</span><span class="p">))</span> |
| <span class="k">return</span> <span class="s2">"</span><span class="si">{}</span><span class="s2">s"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">timedelta</span><span class="p">(</span><span class="n">hours</span><span class="o">=</span><span class="n">val</span><span class="p">)</span><span class="o">.</span><span class="n">seconds</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">match</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span> <span class="o">==</span> <span class="s2">"d"</span><span class="p">:</span> |
| <span class="n">val</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">match</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">1</span><span class="p">))</span> |
| <span class="k">return</span> <span class="s2">"</span><span class="si">{}</span><span class="s2">s"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">timedelta</span><span class="p">(</span><span class="n">days</span><span class="o">=</span><span class="n">val</span><span class="p">)</span><span class="o">.</span><span class="n">seconds</span><span class="p">)</span> |
| |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span> |
| <span class="s2">"DataprocClusterScaleOperator "</span></div> |
| <span class="s2">" should be expressed in day, hours, minutes or seconds. "</span> |
| <span class="s2">" i.e. 1d, 4h, 10m, 30s"</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="DataprocClusterScaleOperator.execute"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocClusterScaleOperator.execute">[docs]</a> <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Scaling cluster: </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">)</span> |
| <span class="n">hook</span> <span class="o">=</span> <span class="n">DataProcHook</span><span class="p">(</span> |
| <span class="n">gcp_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span><span class="p">,</span> |
| <span class="n">delegate_to</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span> |
| <span class="p">)</span> |
| <span class="n">service</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span> |
| |
| <span class="n">update_mask</span> <span class="o">=</span> <span class="s2">"config.worker_config.num_instances,"</span> \ |
| <span class="o">+</span> <span class="s2">"config.secondary_worker_config.num_instances"</span> |
| <span class="n">scaling_cluster_data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_build_scale_cluster_data</span><span class="p">()</span> |
| |
| <span class="n">response</span> <span class="o">=</span> <span class="n">service</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">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">patch</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="bp">self</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">,</span> |
| <span class="n">updateMask</span><span class="o">=</span><span class="n">update_mask</span><span class="p">,</span> |
| <span class="n">body</span><span class="o">=</span><span class="n">scaling_cluster_data</span><span class="p">,</span> |
| <span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">optional_arguments</span> |
| <span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">()</span> |
| <span class="n">operation_name</span> <span class="o">=</span> <span class="n">response</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">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Cluster scale operation name: </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">operation_name</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_wait_for_done</span><span class="p">(</span><span class="n">service</span><span class="p">,</span> <span class="n">operation_name</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="DataprocClusterDeleteOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocClusterDeleteOperator">[docs]</a><span class="k">class</span> <span class="nc">DataprocClusterDeleteOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Delete a cluster on Google Cloud Dataproc. The operator will wait until the</span> |
| <span class="sd"> cluster is destroyed.</span> |
| |
| <span class="sd"> :param cluster_name: The name of the cluster to create. (templated)</span> |
| <span class="sd"> :type cluster_name: str</span> |
| <span class="sd"> :param project_id: The ID of the google cloud project in which</span> |
| <span class="sd"> the cluster runs. (templated)</span> |
| <span class="sd"> :type project_id: str</span> |
| <span class="sd"> :param region: leave as 'global', might become relevant in the future. (templated)</span> |
| <span class="sd"> :type region: str</span> |
| <span class="sd"> :param gcp_conn_id: The connection ID to use connecting to Google Cloud Platform.</span> |
| <span class="sd"> :type gcp_conn_id: str</span> |
| <span class="sd"> :param delegate_to: The account to impersonate, if any.</span> |
| <span class="sd"> For this to work, the service account making the request must have domain-wide</span> |
| <span class="sd"> delegation enabled.</span> |
| <span class="sd"> :type delegate_to: str</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="DataprocClusterDeleteOperator.template_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocClusterDeleteOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'cluster_name'</span><span class="p">,</span> <span class="s1">'project_id'</span><span class="p">,</span> <span class="s1">'region'</span><span class="p">]</span></div> |
| |
| <span class="nd">@apply_defaults</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> |
| <span class="n">cluster_name</span><span class="p">,</span> |
| <span class="n">project_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="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="o">*</span><span class="n">args</span><span class="p">,</span> |
| <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| |
| <span class="nb">super</span><span class="p">(</span><span class="n">DataprocClusterDeleteOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span> <span class="o">=</span> <span class="n">gcp_conn_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span> <span class="o">=</span> <span class="n">delegate_to</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span> <span class="o">=</span> <span class="n">cluster_name</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="nd">@staticmethod</span> |
| <div class="viewcode-block" id="DataprocClusterDeleteOperator._wait_for_done"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocClusterDeleteOperator._wait_for_done">[docs]</a> <span class="k">def</span> <span class="nf">_wait_for_done</span><span class="p">(</span><span class="n">service</span><span class="p">,</span> <span class="n">operation_name</span><span class="p">):</span> |
| <span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="mi">15</span><span class="p">)</span> |
| <span class="k">while</span> <span class="kc">True</span><span class="p">:</span> |
| <span class="n">response</span> <span class="o">=</span> <span class="n">service</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">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="n">operation_name</span> |
| <span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">()</span> |
| |
| <span class="k">if</span> <span class="s1">'done'</span> <span class="ow">in</span> <span class="n">response</span> <span class="ow">and</span> <span class="n">response</span><span class="p">[</span><span class="s1">'done'</span><span class="p">]:</span> |
| <span class="k">if</span> <span class="s1">'error'</span> <span class="ow">in</span> <span class="n">response</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">response</span><span class="p">[</span><span class="s1">'error'</span><span class="p">]))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> |
| <span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="mi">15</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="DataprocClusterDeleteOperator.execute"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocClusterDeleteOperator.execute">[docs]</a> <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Deleting cluster: </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">cluster_name</span><span class="p">)</span> |
| <span class="n">hook</span> <span class="o">=</span> <span class="n">DataProcHook</span><span class="p">(</span> |
| <span class="n">gcp_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span><span class="p">,</span> |
| <span class="n">delegate_to</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span> |
| <span class="p">)</span> |
| <span class="n">service</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span> |
| |
| <span class="n">response</span> <span class="o">=</span> <span class="n">service</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">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">delete</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="bp">self</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">operation_name</span> <span class="o">=</span> <span class="n">response</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">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Cluster delete operation name: </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">operation_name</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_wait_for_done</span><span class="p">(</span><span class="n">service</span><span class="p">,</span> <span class="n">operation_name</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="DataProcPigOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcPigOperator">[docs]</a><span class="k">class</span> <span class="nc">DataProcPigOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Start a Pig query Job on a Cloud DataProc cluster. The parameters of the operation</span> |
| <span class="sd"> will be passed to the cluster.</span> |
| |
| <span class="sd"> It's a good practice to define dataproc_* parameters in the default_args of the dag</span> |
| <span class="sd"> like the cluster name and UDFs.</span> |
| |
| <span class="sd"> .. code-block:: python</span> |
| |
| <span class="sd"> default_args = {</span> |
| <span class="sd"> 'cluster_name': 'cluster-1',</span> |
| <span class="sd"> 'dataproc_pig_jars': [</span> |
| <span class="sd"> 'gs://example/udf/jar/datafu/1.2.0/datafu.jar',</span> |
| <span class="sd"> 'gs://example/udf/jar/gpig/1.2/gpig.jar'</span> |
| <span class="sd"> ]</span> |
| <span class="sd"> }</span> |
| |
| <span class="sd"> You can pass a pig script as string or file reference. Use variables to pass on</span> |
| <span class="sd"> variables for the pig script to be resolved on the cluster or use the parameters to</span> |
| <span class="sd"> be resolved in the script as template parameters.</span> |
| |
| <span class="sd"> **Example**: ::</span> |
| |
| <span class="sd"> t1 = DataProcPigOperator(</span> |
| <span class="sd"> task_id='dataproc_pig',</span> |
| <span class="sd"> query='a_pig_script.pig',</span> |
| <span class="sd"> variables={'out': 'gs://example/output/{{ds}}'},</span> |
| <span class="sd"> dag=dag)</span> |
| |
| <span class="sd"> .. seealso::</span> |
| <span class="sd"> For more detail on about job submission have a look at the reference:</span> |
| <span class="sd"> https://cloud.google.com/dataproc/reference/rest/v1/projects.regions.jobs</span> |
| |
| <span class="sd"> :param query: The query or reference to the query</span> |
| <span class="sd"> file (pg or pig extension). (templated)</span> |
| <span class="sd"> :type query: str</span> |
| <span class="sd"> :param query_uri: The uri of a pig script on Cloud Storage.</span> |
| <span class="sd"> :type query_uri: str</span> |
| <span class="sd"> :param variables: Map of named parameters for the query. (templated)</span> |
| <span class="sd"> :type variables: dict</span> |
| <span class="sd"> :param job_name: The job name used in the DataProc cluster. This</span> |
| <span class="sd"> name by default is the task_id appended with the execution data, but can</span> |
| <span class="sd"> be templated. The name will always be appended with a random number to</span> |
| <span class="sd"> avoid name clashes. (templated)</span> |
| <span class="sd"> :type job_name: str</span> |
| <span class="sd"> :param cluster_name: The name of the DataProc cluster. (templated)</span> |
| <span class="sd"> :type cluster_name: str</span> |
| <span class="sd"> :param dataproc_pig_properties: Map for the Pig properties. Ideal to put in</span> |
| <span class="sd"> default arguments</span> |
| <span class="sd"> :type dataproc_pig_properties: dict</span> |
| <span class="sd"> :param dataproc_pig_jars: URIs to jars provisioned in Cloud Storage (example: for</span> |
| <span class="sd"> UDFs and libs) and are ideal to put in default arguments.</span> |
| <span class="sd"> :type dataproc_pig_jars: list</span> |
| <span class="sd"> :param gcp_conn_id: The connection ID to use connecting to Google Cloud Platform.</span> |
| <span class="sd"> :type gcp_conn_id: str</span> |
| <span class="sd"> :param delegate_to: The account to impersonate, if any.</span> |
| <span class="sd"> For this to work, the service account making the request must have domain-wide</span> |
| <span class="sd"> delegation enabled.</span> |
| <span class="sd"> :type delegate_to: str</span> |
| <span class="sd"> :param region: The specified region where the dataproc cluster is created.</span> |
| <span class="sd"> :type region: str</span> |
| <span class="sd"> :param job_error_states: Job states that should be considered error states.</span> |
| <span class="sd"> Any states in this list will result in an error being raised and failure of the</span> |
| <span class="sd"> task. Eg, if the ``CANCELLED`` state should also be considered a task failure,</span> |
| <span class="sd"> pass in ``['ERROR', 'CANCELLED']``. Possible values are currently only</span> |
| <span class="sd"> ``'ERROR'`` and ``'CANCELLED'``, but could change in the future. Defaults to</span> |
| <span class="sd"> ``['ERROR']``.</span> |
| <span class="sd"> :type job_error_states: list</span> |
| <span class="sd"> :var dataproc_job_id: The actual "jobId" as submitted to the Dataproc API.</span> |
| <span class="sd"> This is useful for identifying or linking to the job in the Google Cloud Console</span> |
| <span class="sd"> Dataproc UI, as the actual "jobId" submitted to the Dataproc API is appended with</span> |
| <span class="sd"> an 8 character random string.</span> |
| <span class="sd"> :vartype dataproc_job_id: str</span> |
| <span class="sd"> """</span> |
| <div class="viewcode-block" id="DataProcPigOperator.template_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcPigOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'query'</span><span class="p">,</span> <span class="s1">'variables'</span><span class="p">,</span> <span class="s1">'job_name'</span><span class="p">,</span> <span class="s1">'cluster_name'</span><span class="p">,</span> <span class="s1">'region'</span><span class="p">,</span> <span class="s1">'dataproc_jars'</span><span class="p">]</span></div> |
| <div class="viewcode-block" id="DataProcPigOperator.template_ext"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcPigOperator.template_ext">[docs]</a> <span class="n">template_ext</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'.pg'</span><span class="p">,</span> <span class="s1">'.pig'</span><span class="p">,)</span></div> |
| <div class="viewcode-block" id="DataProcPigOperator.ui_color"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcPigOperator.ui_color">[docs]</a> <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#0273d4'</span></div> |
| |
| <span class="nd">@apply_defaults</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">query</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">query_uri</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">variables</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">job_name</span><span class="o">=</span><span class="s1">'{{task.task_id}}_{{ds_nodash}}'</span><span class="p">,</span> |
| <span class="n">cluster_name</span><span class="o">=</span><span class="s1">'cluster-1'</span><span class="p">,</span> |
| <span class="n">dataproc_pig_properties</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">dataproc_pig_jars</span><span class="o">=</span><span class="kc">None</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">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="p">[</span><span class="s1">'ERROR'</span><span class="p">],</span> |
| <span class="o">*</span><span class="n">args</span><span class="p">,</span> |
| <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| |
| <span class="nb">super</span><span class="p">(</span><span class="n">DataProcPigOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span> <span class="o">=</span> <span class="n">gcp_conn_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span> <span class="o">=</span> <span class="n">delegate_to</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">query</span> <span class="o">=</span> <span class="n">query</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">query_uri</span> <span class="o">=</span> <span class="n">query_uri</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">variables</span> <span class="o">=</span> <span class="n">variables</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">job_name</span> <span class="o">=</span> <span class="n">job_name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span> <span class="o">=</span> <span class="n">cluster_name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_properties</span> <span class="o">=</span> <span class="n">dataproc_pig_properties</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_jars</span> <span class="o">=</span> <span class="n">dataproc_pig_jars</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_error_states</span> <span class="o">=</span> <span class="n">job_error_states</span> |
| |
| <div class="viewcode-block" id="DataProcPigOperator.execute"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcPigOperator.execute">[docs]</a> <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> |
| <span class="n">hook</span> <span class="o">=</span> <span class="n">DataProcHook</span><span class="p">(</span><span class="n">gcp_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span><span class="p">,</span> |
| <span class="n">delegate_to</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span><span class="p">)</span> |
| <span class="n">job</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">create_job_template</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">task_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">,</span> <span class="s2">"pigJob"</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_properties</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">query</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_query_uri</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">query_uri</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_query</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">query</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_variables</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">variables</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_jar_file_uris</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">dataproc_jars</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">set_job_name</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">job_name</span><span class="p">)</span> |
| |
| <span class="n">job_to_submit</span> <span class="o">=</span> <span class="n">job</span><span class="o">.</span><span class="n">build</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_job_id</span> <span class="o">=</span> <span class="n">job_to_submit</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="n">hook</span><span class="o">.</span><span class="n">submit</span><span class="p">(</span><span class="n">hook</span><span class="o">.</span><span class="n">project_id</span><span class="p">,</span> <span class="n">job_to_submit</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="bp">self</span><span class="o">.</span><span class="n">job_error_states</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="DataProcHiveOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcHiveOperator">[docs]</a><span class="k">class</span> <span class="nc">DataProcHiveOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Start a Hive query Job on a Cloud DataProc cluster.</span> |
| |
| <span class="sd"> :param query: The query or reference to the query file (q extension).</span> |
| <span class="sd"> :type query: str</span> |
| <span class="sd"> :param query_uri: The uri of a hive script on Cloud Storage.</span> |
| <span class="sd"> :type query_uri: str</span> |
| <span class="sd"> :param variables: Map of named parameters for the query.</span> |
| <span class="sd"> :type variables: dict</span> |
| <span class="sd"> :param job_name: The job name used in the DataProc cluster. This name by default</span> |
| <span class="sd"> is the task_id appended with the execution data, but can be templated. The</span> |
| <span class="sd"> name will always be appended with a random number to avoid name clashes.</span> |
| <span class="sd"> :type job_name: str</span> |
| <span class="sd"> :param cluster_name: The name of the DataProc cluster.</span> |
| <span class="sd"> :type cluster_name: str</span> |
| <span class="sd"> :param dataproc_hive_properties: Map for the Pig properties. Ideal to put in</span> |
| <span class="sd"> default arguments</span> |
| <span class="sd"> :type dataproc_hive_properties: dict</span> |
| <span class="sd"> :param dataproc_hive_jars: URIs to jars provisioned in Cloud Storage (example: for</span> |
| <span class="sd"> UDFs and libs) and are ideal to put in default arguments.</span> |
| <span class="sd"> :type dataproc_hive_jars: list</span> |
| <span class="sd"> :param gcp_conn_id: The connection ID to use connecting to Google Cloud Platform.</span> |
| <span class="sd"> :type gcp_conn_id: str</span> |
| <span class="sd"> :param delegate_to: The account to impersonate, if any.</span> |
| <span class="sd"> For this to work, the service account making the request must have domain-wide</span> |
| <span class="sd"> delegation enabled.</span> |
| <span class="sd"> :type delegate_to: str</span> |
| <span class="sd"> :param region: The specified region where the dataproc cluster is created.</span> |
| <span class="sd"> :type region: str</span> |
| <span class="sd"> :param job_error_states: Job states that should be considered error states.</span> |
| <span class="sd"> Any states in this list will result in an error being raised and failure of the</span> |
| <span class="sd"> task. Eg, if the ``CANCELLED`` state should also be considered a task failure,</span> |
| <span class="sd"> pass in ``['ERROR', 'CANCELLED']``. Possible values are currently only</span> |
| <span class="sd"> ``'ERROR'`` and ``'CANCELLED'``, but could change in the future. Defaults to</span> |
| <span class="sd"> ``['ERROR']``.</span> |
| <span class="sd"> :type job_error_states: list</span> |
| <span class="sd"> :var dataproc_job_id: The actual "jobId" as submitted to the Dataproc API.</span> |
| <span class="sd"> This is useful for identifying or linking to the job in the Google Cloud Console</span> |
| <span class="sd"> Dataproc UI, as the actual "jobId" submitted to the Dataproc API is appended with</span> |
| <span class="sd"> an 8 character random string.</span> |
| <span class="sd"> :vartype dataproc_job_id: str</span> |
| <span class="sd"> """</span> |
| <div class="viewcode-block" id="DataProcHiveOperator.template_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcHiveOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'query'</span><span class="p">,</span> <span class="s1">'variables'</span><span class="p">,</span> <span class="s1">'job_name'</span><span class="p">,</span> <span class="s1">'cluster_name'</span><span class="p">,</span> <span class="s1">'region'</span><span class="p">,</span> <span class="s1">'dataproc_jars'</span><span class="p">]</span></div> |
| <div class="viewcode-block" id="DataProcHiveOperator.template_ext"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcHiveOperator.template_ext">[docs]</a> <span class="n">template_ext</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'.q'</span><span class="p">,)</span></div> |
| <div class="viewcode-block" id="DataProcHiveOperator.ui_color"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcHiveOperator.ui_color">[docs]</a> <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#0273d4'</span></div> |
| |
| <span class="nd">@apply_defaults</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">query</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">query_uri</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">variables</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">job_name</span><span class="o">=</span><span class="s1">'{{task.task_id}}_{{ds_nodash}}'</span><span class="p">,</span> |
| <span class="n">cluster_name</span><span class="o">=</span><span class="s1">'cluster-1'</span><span class="p">,</span> |
| <span class="n">dataproc_hive_properties</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">dataproc_hive_jars</span><span class="o">=</span><span class="kc">None</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">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="p">[</span><span class="s1">'ERROR'</span><span class="p">],</span> |
| <span class="o">*</span><span class="n">args</span><span class="p">,</span> |
| <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| |
| <span class="nb">super</span><span class="p">(</span><span class="n">DataProcHiveOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span> <span class="o">=</span> <span class="n">gcp_conn_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span> <span class="o">=</span> <span class="n">delegate_to</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">query</span> <span class="o">=</span> <span class="n">query</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">query_uri</span> <span class="o">=</span> <span class="n">query_uri</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">variables</span> <span class="o">=</span> <span class="n">variables</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">job_name</span> <span class="o">=</span> <span class="n">job_name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span> <span class="o">=</span> <span class="n">cluster_name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_properties</span> <span class="o">=</span> <span class="n">dataproc_hive_properties</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_jars</span> <span class="o">=</span> <span class="n">dataproc_hive_jars</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_error_states</span> <span class="o">=</span> <span class="n">job_error_states</span> |
| |
| <div class="viewcode-block" id="DataProcHiveOperator.execute"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcHiveOperator.execute">[docs]</a> <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> |
| <span class="n">hook</span> <span class="o">=</span> <span class="n">DataProcHook</span><span class="p">(</span><span class="n">gcp_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span><span class="p">,</span> |
| <span class="n">delegate_to</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span><span class="p">)</span> |
| |
| <span class="n">job</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">create_job_template</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">task_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">,</span> <span class="s2">"hiveJob"</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_properties</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">query</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_query_uri</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">query_uri</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_query</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">query</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_variables</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">variables</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_jar_file_uris</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">dataproc_jars</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">set_job_name</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">job_name</span><span class="p">)</span> |
| |
| <span class="n">job_to_submit</span> <span class="o">=</span> <span class="n">job</span><span class="o">.</span><span class="n">build</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_job_id</span> <span class="o">=</span> <span class="n">job_to_submit</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="n">hook</span><span class="o">.</span><span class="n">submit</span><span class="p">(</span><span class="n">hook</span><span class="o">.</span><span class="n">project_id</span><span class="p">,</span> <span class="n">job_to_submit</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="bp">self</span><span class="o">.</span><span class="n">job_error_states</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="DataProcSparkSqlOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcSparkSqlOperator">[docs]</a><span class="k">class</span> <span class="nc">DataProcSparkSqlOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Start a Spark SQL query Job on a Cloud DataProc cluster.</span> |
| |
| <span class="sd"> :param query: The query or reference to the query file (q extension). (templated)</span> |
| <span class="sd"> :type query: str</span> |
| <span class="sd"> :param query_uri: The uri of a spark sql script on Cloud Storage.</span> |
| <span class="sd"> :type query_uri: str</span> |
| <span class="sd"> :param variables: Map of named parameters for the query. (templated)</span> |
| <span class="sd"> :type variables: dict</span> |
| <span class="sd"> :param job_name: The job name used in the DataProc cluster. This</span> |
| <span class="sd"> name by default is the task_id appended with the execution data, but can</span> |
| <span class="sd"> be templated. The name will always be appended with a random number to</span> |
| <span class="sd"> avoid name clashes. (templated)</span> |
| <span class="sd"> :type job_name: str</span> |
| <span class="sd"> :param cluster_name: The name of the DataProc cluster. (templated)</span> |
| <span class="sd"> :type cluster_name: str</span> |
| <span class="sd"> :param dataproc_spark_properties: Map for the Pig properties. Ideal to put in</span> |
| <span class="sd"> default arguments</span> |
| <span class="sd"> :type dataproc_spark_properties: dict</span> |
| <span class="sd"> :param dataproc_spark_jars: URIs to jars provisioned in Cloud Storage (example:</span> |
| <span class="sd"> for UDFs and libs) and are ideal to put in default arguments.</span> |
| <span class="sd"> :type dataproc_spark_jars: list</span> |
| <span class="sd"> :param gcp_conn_id: The connection ID to use connecting to Google Cloud Platform.</span> |
| <span class="sd"> :type gcp_conn_id: str</span> |
| <span class="sd"> :param delegate_to: The account to impersonate, if any.</span> |
| <span class="sd"> For this to work, the service account making the request must have domain-wide</span> |
| <span class="sd"> delegation enabled.</span> |
| <span class="sd"> :type delegate_to: str</span> |
| <span class="sd"> :param region: The specified region where the dataproc cluster is created.</span> |
| <span class="sd"> :type region: str</span> |
| <span class="sd"> :param job_error_states: Job states that should be considered error states.</span> |
| <span class="sd"> Any states in this list will result in an error being raised and failure of the</span> |
| <span class="sd"> task. Eg, if the ``CANCELLED`` state should also be considered a task failure,</span> |
| <span class="sd"> pass in ``['ERROR', 'CANCELLED']``. Possible values are currently only</span> |
| <span class="sd"> ``'ERROR'`` and ``'CANCELLED'``, but could change in the future. Defaults to</span> |
| <span class="sd"> ``['ERROR']``.</span> |
| <span class="sd"> :type job_error_states: list</span> |
| <span class="sd"> :var dataproc_job_id: The actual "jobId" as submitted to the Dataproc API.</span> |
| <span class="sd"> This is useful for identifying or linking to the job in the Google Cloud Console</span> |
| <span class="sd"> Dataproc UI, as the actual "jobId" submitted to the Dataproc API is appended with</span> |
| <span class="sd"> an 8 character random string.</span> |
| <span class="sd"> :vartype dataproc_job_id: str</span> |
| <span class="sd"> """</span> |
| <div class="viewcode-block" id="DataProcSparkSqlOperator.template_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcSparkSqlOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'query'</span><span class="p">,</span> <span class="s1">'variables'</span><span class="p">,</span> <span class="s1">'job_name'</span><span class="p">,</span> <span class="s1">'cluster_name'</span><span class="p">,</span> <span class="s1">'region'</span><span class="p">,</span> <span class="s1">'dataproc_jars'</span><span class="p">]</span></div> |
| <div class="viewcode-block" id="DataProcSparkSqlOperator.template_ext"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcSparkSqlOperator.template_ext">[docs]</a> <span class="n">template_ext</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'.q'</span><span class="p">,)</span></div> |
| <div class="viewcode-block" id="DataProcSparkSqlOperator.ui_color"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcSparkSqlOperator.ui_color">[docs]</a> <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#0273d4'</span></div> |
| |
| <span class="nd">@apply_defaults</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">query</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">query_uri</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">variables</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">job_name</span><span class="o">=</span><span class="s1">'{{task.task_id}}_{{ds_nodash}}'</span><span class="p">,</span> |
| <span class="n">cluster_name</span><span class="o">=</span><span class="s1">'cluster-1'</span><span class="p">,</span> |
| <span class="n">dataproc_spark_properties</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">dataproc_spark_jars</span><span class="o">=</span><span class="kc">None</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">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="p">[</span><span class="s1">'ERROR'</span><span class="p">],</span> |
| <span class="o">*</span><span class="n">args</span><span class="p">,</span> |
| <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| |
| <span class="nb">super</span><span class="p">(</span><span class="n">DataProcSparkSqlOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span> <span class="o">=</span> <span class="n">gcp_conn_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span> <span class="o">=</span> <span class="n">delegate_to</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">query</span> <span class="o">=</span> <span class="n">query</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">query_uri</span> <span class="o">=</span> <span class="n">query_uri</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">variables</span> <span class="o">=</span> <span class="n">variables</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">job_name</span> <span class="o">=</span> <span class="n">job_name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span> <span class="o">=</span> <span class="n">cluster_name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_properties</span> <span class="o">=</span> <span class="n">dataproc_spark_properties</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_jars</span> <span class="o">=</span> <span class="n">dataproc_spark_jars</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_error_states</span> <span class="o">=</span> <span class="n">job_error_states</span> |
| |
| <div class="viewcode-block" id="DataProcSparkSqlOperator.execute"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcSparkSqlOperator.execute">[docs]</a> <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> |
| <span class="n">hook</span> <span class="o">=</span> <span class="n">DataProcHook</span><span class="p">(</span><span class="n">gcp_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span><span class="p">,</span> |
| <span class="n">delegate_to</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span><span class="p">)</span> |
| |
| <span class="n">job</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">create_job_template</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">task_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">,</span> <span class="s2">"sparkSqlJob"</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_properties</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">query</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_query_uri</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">query_uri</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_query</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">query</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_variables</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">variables</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_jar_file_uris</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">dataproc_jars</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">set_job_name</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">job_name</span><span class="p">)</span> |
| |
| <span class="n">job_to_submit</span> <span class="o">=</span> <span class="n">job</span><span class="o">.</span><span class="n">build</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_job_id</span> <span class="o">=</span> <span class="n">job_to_submit</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="n">hook</span><span class="o">.</span><span class="n">submit</span><span class="p">(</span><span class="n">hook</span><span class="o">.</span><span class="n">project_id</span><span class="p">,</span> <span class="n">job_to_submit</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="bp">self</span><span class="o">.</span><span class="n">job_error_states</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="DataProcSparkOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcSparkOperator">[docs]</a><span class="k">class</span> <span class="nc">DataProcSparkOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Start a Spark Job on a Cloud DataProc cluster.</span> |
| |
| <span class="sd"> :param main_jar: URI of the job jar provisioned on Cloud Storage. (use this or</span> |
| <span class="sd"> the main_class, not both together).</span> |
| <span class="sd"> :type main_jar: str</span> |
| <span class="sd"> :param main_class: Name of the job class. (use this or the main_jar, not both</span> |
| <span class="sd"> together).</span> |
| <span class="sd"> :type main_class: str</span> |
| <span class="sd"> :param arguments: Arguments for the job. (templated)</span> |
| <span class="sd"> :type arguments: list</span> |
| <span class="sd"> :param archives: List of archived files that will be unpacked in the work</span> |
| <span class="sd"> directory. Should be stored in Cloud Storage.</span> |
| <span class="sd"> :type archives: list</span> |
| <span class="sd"> :param files: List of files to be copied to the working directory</span> |
| <span class="sd"> :type files: list</span> |
| <span class="sd"> :param job_name: The job name used in the DataProc cluster. This</span> |
| <span class="sd"> name by default is the task_id appended with the execution data, but can</span> |
| <span class="sd"> be templated. The name will always be appended with a random number to</span> |
| <span class="sd"> avoid name clashes. (templated)</span> |
| <span class="sd"> :type job_name: str</span> |
| <span class="sd"> :param cluster_name: The name of the DataProc cluster. (templated)</span> |
| <span class="sd"> :type cluster_name: str</span> |
| <span class="sd"> :param dataproc_spark_properties: Map for the Pig properties. Ideal to put in</span> |
| <span class="sd"> default arguments</span> |
| <span class="sd"> :type dataproc_spark_properties: dict</span> |
| <span class="sd"> :param dataproc_spark_jars: URIs to jars provisioned in Cloud Storage (example:</span> |
| <span class="sd"> for UDFs and libs) and are ideal to put in default arguments.</span> |
| <span class="sd"> :type dataproc_spark_jars: list</span> |
| <span class="sd"> :param gcp_conn_id: The connection ID to use connecting to Google Cloud Platform.</span> |
| <span class="sd"> :type gcp_conn_id: str</span> |
| <span class="sd"> :param delegate_to: The account to impersonate, if any.</span> |
| <span class="sd"> For this to work, the service account making the request must have domain-wide</span> |
| <span class="sd"> delegation enabled.</span> |
| <span class="sd"> :type delegate_to: str</span> |
| <span class="sd"> :param region: The specified region where the dataproc cluster is created.</span> |
| <span class="sd"> :type region: str</span> |
| <span class="sd"> :param job_error_states: Job states that should be considered error states.</span> |
| <span class="sd"> Any states in this list will result in an error being raised and failure of the</span> |
| <span class="sd"> task. Eg, if the ``CANCELLED`` state should also be considered a task failure,</span> |
| <span class="sd"> pass in ``['ERROR', 'CANCELLED']``. Possible values are currently only</span> |
| <span class="sd"> ``'ERROR'`` and ``'CANCELLED'``, but could change in the future. Defaults to</span> |
| <span class="sd"> ``['ERROR']``.</span> |
| <span class="sd"> :type job_error_states: list</span> |
| <span class="sd"> :var dataproc_job_id: The actual "jobId" as submitted to the Dataproc API.</span> |
| <span class="sd"> This is useful for identifying or linking to the job in the Google Cloud Console</span> |
| <span class="sd"> Dataproc UI, as the actual "jobId" submitted to the Dataproc API is appended with</span> |
| <span class="sd"> an 8 character random string.</span> |
| <span class="sd"> :vartype dataproc_job_id: str</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="DataProcSparkOperator.template_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcSparkOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'arguments'</span><span class="p">,</span> <span class="s1">'job_name'</span><span class="p">,</span> <span class="s1">'cluster_name'</span><span class="p">,</span> <span class="s1">'region'</span><span class="p">,</span> <span class="s1">'dataproc_jars'</span><span class="p">]</span></div> |
| <div class="viewcode-block" id="DataProcSparkOperator.ui_color"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcSparkOperator.ui_color">[docs]</a> <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#0273d4'</span></div> |
| |
| <span class="nd">@apply_defaults</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">main_jar</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">main_class</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">arguments</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">archives</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">files</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">job_name</span><span class="o">=</span><span class="s1">'{{task.task_id}}_{{ds_nodash}}'</span><span class="p">,</span> |
| <span class="n">cluster_name</span><span class="o">=</span><span class="s1">'cluster-1'</span><span class="p">,</span> |
| <span class="n">dataproc_spark_properties</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">dataproc_spark_jars</span><span class="o">=</span><span class="kc">None</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">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="p">[</span><span class="s1">'ERROR'</span><span class="p">],</span> |
| <span class="o">*</span><span class="n">args</span><span class="p">,</span> |
| <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| |
| <span class="nb">super</span><span class="p">(</span><span class="n">DataProcSparkOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span> <span class="o">=</span> <span class="n">gcp_conn_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span> <span class="o">=</span> <span class="n">delegate_to</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">main_jar</span> <span class="o">=</span> <span class="n">main_jar</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">main_class</span> <span class="o">=</span> <span class="n">main_class</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">arguments</span> <span class="o">=</span> <span class="n">arguments</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">archives</span> <span class="o">=</span> <span class="n">archives</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">files</span> <span class="o">=</span> <span class="n">files</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">job_name</span> <span class="o">=</span> <span class="n">job_name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span> <span class="o">=</span> <span class="n">cluster_name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_properties</span> <span class="o">=</span> <span class="n">dataproc_spark_properties</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_jars</span> <span class="o">=</span> <span class="n">dataproc_spark_jars</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_error_states</span> <span class="o">=</span> <span class="n">job_error_states</span> |
| |
| <div class="viewcode-block" id="DataProcSparkOperator.execute"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcSparkOperator.execute">[docs]</a> <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> |
| <span class="n">hook</span> <span class="o">=</span> <span class="n">DataProcHook</span><span class="p">(</span><span class="n">gcp_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span><span class="p">,</span> |
| <span class="n">delegate_to</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span><span class="p">)</span> |
| <span class="n">job</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">create_job_template</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">task_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">,</span> <span class="s2">"sparkJob"</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_properties</span><span class="p">)</span> |
| |
| <span class="n">job</span><span class="o">.</span><span class="n">set_main</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">main_jar</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">main_class</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_args</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">arguments</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_jar_file_uris</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">dataproc_jars</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_archive_uris</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">archives</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_file_uris</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">files</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">set_job_name</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">job_name</span><span class="p">)</span> |
| |
| <span class="n">job_to_submit</span> <span class="o">=</span> <span class="n">job</span><span class="o">.</span><span class="n">build</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_job_id</span> <span class="o">=</span> <span class="n">job_to_submit</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="n">hook</span><span class="o">.</span><span class="n">submit</span><span class="p">(</span><span class="n">hook</span><span class="o">.</span><span class="n">project_id</span><span class="p">,</span> <span class="n">job_to_submit</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="bp">self</span><span class="o">.</span><span class="n">job_error_states</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="DataProcHadoopOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcHadoopOperator">[docs]</a><span class="k">class</span> <span class="nc">DataProcHadoopOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Start a Hadoop Job on a Cloud DataProc cluster.</span> |
| |
| <span class="sd"> :param main_jar: URI of the job jar provisioned on Cloud Storage. (use this or</span> |
| <span class="sd"> the main_class, not both together).</span> |
| <span class="sd"> :type main_jar: str</span> |
| <span class="sd"> :param main_class: Name of the job class. (use this or the main_jar, not both</span> |
| <span class="sd"> together).</span> |
| <span class="sd"> :type main_class: str</span> |
| <span class="sd"> :param arguments: Arguments for the job. (templated)</span> |
| <span class="sd"> :type arguments: list</span> |
| <span class="sd"> :param archives: List of archived files that will be unpacked in the work</span> |
| <span class="sd"> directory. Should be stored in Cloud Storage.</span> |
| <span class="sd"> :type archives: list</span> |
| <span class="sd"> :param files: List of files to be copied to the working directory</span> |
| <span class="sd"> :type files: list</span> |
| <span class="sd"> :param job_name: The job name used in the DataProc cluster. This</span> |
| <span class="sd"> name by default is the task_id appended with the execution data, but can</span> |
| <span class="sd"> be templated. The name will always be appended with a random number to</span> |
| <span class="sd"> avoid name clashes. (templated)</span> |
| <span class="sd"> :type job_name: str</span> |
| <span class="sd"> :param cluster_name: The name of the DataProc cluster. (templated)</span> |
| <span class="sd"> :type cluster_name: str</span> |
| <span class="sd"> :param dataproc_hadoop_properties: Map for the Pig properties. Ideal to put in</span> |
| <span class="sd"> default arguments</span> |
| <span class="sd"> :type dataproc_hadoop_properties: dict</span> |
| <span class="sd"> :param dataproc_hadoop_jars: URIs to jars provisioned in Cloud Storage (example:</span> |
| <span class="sd"> for UDFs and libs) and are ideal to put in default arguments.</span> |
| <span class="sd"> :type dataproc_hadoop_jars: list</span> |
| <span class="sd"> :param gcp_conn_id: The connection ID to use connecting to Google Cloud Platform.</span> |
| <span class="sd"> :type gcp_conn_id: str</span> |
| <span class="sd"> :param delegate_to: The account to impersonate, if any.</span> |
| <span class="sd"> For this to work, the service account making the request must have domain-wide</span> |
| <span class="sd"> delegation enabled.</span> |
| <span class="sd"> :type delegate_to: str</span> |
| <span class="sd"> :param region: The specified region where the dataproc cluster is created.</span> |
| <span class="sd"> :type region: str</span> |
| <span class="sd"> :param job_error_states: Job states that should be considered error states.</span> |
| <span class="sd"> Any states in this list will result in an error being raised and failure of the</span> |
| <span class="sd"> task. Eg, if the ``CANCELLED`` state should also be considered a task failure,</span> |
| <span class="sd"> pass in ``['ERROR', 'CANCELLED']``. Possible values are currently only</span> |
| <span class="sd"> ``'ERROR'`` and ``'CANCELLED'``, but could change in the future. Defaults to</span> |
| <span class="sd"> ``['ERROR']``.</span> |
| <span class="sd"> :type job_error_states: list</span> |
| <span class="sd"> :var dataproc_job_id: The actual "jobId" as submitted to the Dataproc API.</span> |
| <span class="sd"> This is useful for identifying or linking to the job in the Google Cloud Console</span> |
| <span class="sd"> Dataproc UI, as the actual "jobId" submitted to the Dataproc API is appended with</span> |
| <span class="sd"> an 8 character random string.</span> |
| <span class="sd"> :vartype dataproc_job_id: str</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="DataProcHadoopOperator.template_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcHadoopOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'arguments'</span><span class="p">,</span> <span class="s1">'job_name'</span><span class="p">,</span> <span class="s1">'cluster_name'</span><span class="p">,</span> <span class="s1">'region'</span><span class="p">,</span> <span class="s1">'dataproc_jars'</span><span class="p">]</span></div> |
| <div class="viewcode-block" id="DataProcHadoopOperator.ui_color"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcHadoopOperator.ui_color">[docs]</a> <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#0273d4'</span></div> |
| |
| <span class="nd">@apply_defaults</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">main_jar</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">main_class</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">arguments</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">archives</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">files</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">job_name</span><span class="o">=</span><span class="s1">'{{task.task_id}}_{{ds_nodash}}'</span><span class="p">,</span> |
| <span class="n">cluster_name</span><span class="o">=</span><span class="s1">'cluster-1'</span><span class="p">,</span> |
| <span class="n">dataproc_hadoop_properties</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">dataproc_hadoop_jars</span><span class="o">=</span><span class="kc">None</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">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="p">[</span><span class="s1">'ERROR'</span><span class="p">],</span> |
| <span class="o">*</span><span class="n">args</span><span class="p">,</span> |
| <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| |
| <span class="nb">super</span><span class="p">(</span><span class="n">DataProcHadoopOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span> <span class="o">=</span> <span class="n">gcp_conn_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span> <span class="o">=</span> <span class="n">delegate_to</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">main_jar</span> <span class="o">=</span> <span class="n">main_jar</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">main_class</span> <span class="o">=</span> <span class="n">main_class</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">arguments</span> <span class="o">=</span> <span class="n">arguments</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">archives</span> <span class="o">=</span> <span class="n">archives</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">files</span> <span class="o">=</span> <span class="n">files</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">job_name</span> <span class="o">=</span> <span class="n">job_name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span> <span class="o">=</span> <span class="n">cluster_name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_properties</span> <span class="o">=</span> <span class="n">dataproc_hadoop_properties</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_jars</span> <span class="o">=</span> <span class="n">dataproc_hadoop_jars</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_error_states</span> <span class="o">=</span> <span class="n">job_error_states</span> |
| |
| <div class="viewcode-block" id="DataProcHadoopOperator.execute"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcHadoopOperator.execute">[docs]</a> <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> |
| <span class="n">hook</span> <span class="o">=</span> <span class="n">DataProcHook</span><span class="p">(</span><span class="n">gcp_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span><span class="p">,</span> |
| <span class="n">delegate_to</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span><span class="p">)</span> |
| <span class="n">job</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">create_job_template</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">task_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">,</span> <span class="s2">"hadoopJob"</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_properties</span><span class="p">)</span> |
| |
| <span class="n">job</span><span class="o">.</span><span class="n">set_main</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">main_jar</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">main_class</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_args</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">arguments</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_jar_file_uris</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">dataproc_jars</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_archive_uris</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">archives</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_file_uris</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">files</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">set_job_name</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">job_name</span><span class="p">)</span> |
| |
| <span class="n">job_to_submit</span> <span class="o">=</span> <span class="n">job</span><span class="o">.</span><span class="n">build</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_job_id</span> <span class="o">=</span> <span class="n">job_to_submit</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="n">hook</span><span class="o">.</span><span class="n">submit</span><span class="p">(</span><span class="n">hook</span><span class="o">.</span><span class="n">project_id</span><span class="p">,</span> <span class="n">job_to_submit</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="bp">self</span><span class="o">.</span><span class="n">job_error_states</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="DataProcPySparkOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcPySparkOperator">[docs]</a><span class="k">class</span> <span class="nc">DataProcPySparkOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Start a PySpark Job on a Cloud DataProc cluster.</span> |
| |
| <span class="sd"> :param main: [Required] The Hadoop Compatible Filesystem (HCFS) URI of the main</span> |
| <span class="sd"> Python file to use as the driver. Must be a .py file.</span> |
| <span class="sd"> :type main: str</span> |
| <span class="sd"> :param arguments: Arguments for the job. (templated)</span> |
| <span class="sd"> :type arguments: list</span> |
| <span class="sd"> :param archives: List of archived files that will be unpacked in the work</span> |
| <span class="sd"> directory. Should be stored in Cloud Storage.</span> |
| <span class="sd"> :type archives: list</span> |
| <span class="sd"> :param files: List of files to be copied to the working directory</span> |
| <span class="sd"> :type files: list</span> |
| <span class="sd"> :param pyfiles: List of Python files to pass to the PySpark framework.</span> |
| <span class="sd"> Supported file types: .py, .egg, and .zip</span> |
| <span class="sd"> :type pyfiles: list</span> |
| <span class="sd"> :param job_name: The job name used in the DataProc cluster. This</span> |
| <span class="sd"> name by default is the task_id appended with the execution data, but can</span> |
| <span class="sd"> be templated. The name will always be appended with a random number to</span> |
| <span class="sd"> avoid name clashes. (templated)</span> |
| <span class="sd"> :type job_name: str</span> |
| <span class="sd"> :param cluster_name: The name of the DataProc cluster.</span> |
| <span class="sd"> :type cluster_name: str</span> |
| <span class="sd"> :param dataproc_pyspark_properties: Map for the Pig properties. Ideal to put in</span> |
| <span class="sd"> default arguments</span> |
| <span class="sd"> :type dataproc_pyspark_properties: dict</span> |
| <span class="sd"> :param dataproc_pyspark_jars: URIs to jars provisioned in Cloud Storage (example:</span> |
| <span class="sd"> for UDFs and libs) and are ideal to put in default arguments.</span> |
| <span class="sd"> :type dataproc_pyspark_jars: list</span> |
| <span class="sd"> :param gcp_conn_id: The connection ID to use connecting to Google Cloud Platform.</span> |
| <span class="sd"> :type gcp_conn_id: str</span> |
| <span class="sd"> :param delegate_to: The account to impersonate, if any.</span> |
| <span class="sd"> For this to work, the service account making the request must have</span> |
| <span class="sd"> domain-wide delegation enabled.</span> |
| <span class="sd"> :type delegate_to: str</span> |
| <span class="sd"> :param region: The specified region where the dataproc cluster is created.</span> |
| <span class="sd"> :type region: str</span> |
| <span class="sd"> :param job_error_states: Job states that should be considered error states.</span> |
| <span class="sd"> Any states in this list will result in an error being raised and failure of the</span> |
| <span class="sd"> task. Eg, if the ``CANCELLED`` state should also be considered a task failure,</span> |
| <span class="sd"> pass in ``['ERROR', 'CANCELLED']``. Possible values are currently only</span> |
| <span class="sd"> ``'ERROR'`` and ``'CANCELLED'``, but could change in the future. Defaults to</span> |
| <span class="sd"> ``['ERROR']``.</span> |
| <span class="sd"> :type job_error_states: list</span> |
| <span class="sd"> :var dataproc_job_id: The actual "jobId" as submitted to the Dataproc API.</span> |
| <span class="sd"> This is useful for identifying or linking to the job in the Google Cloud Console</span> |
| <span class="sd"> Dataproc UI, as the actual "jobId" submitted to the Dataproc API is appended with</span> |
| <span class="sd"> an 8 character random string.</span> |
| <span class="sd"> :vartype dataproc_job_id: str</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="DataProcPySparkOperator.template_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcPySparkOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'arguments'</span><span class="p">,</span> <span class="s1">'job_name'</span><span class="p">,</span> <span class="s1">'cluster_name'</span><span class="p">,</span> <span class="s1">'region'</span><span class="p">,</span> <span class="s1">'dataproc_jars'</span><span class="p">]</span></div> |
| <div class="viewcode-block" id="DataProcPySparkOperator.ui_color"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcPySparkOperator.ui_color">[docs]</a> <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#0273d4'</span></div> |
| |
| <span class="nd">@staticmethod</span> |
| <div class="viewcode-block" id="DataProcPySparkOperator._generate_temp_filename"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcPySparkOperator._generate_temp_filename">[docs]</a> <span class="k">def</span> <span class="nf">_generate_temp_filename</span><span class="p">(</span><span class="n">filename</span><span class="p">):</span> |
| <span class="n">dt</span> <span class="o">=</span> <span class="n">time</span><span class="o">.</span><span class="n">strftime</span><span class="p">(</span><span class="s1">'%Y%m</span><span class="si">%d</span><span class="s1">%H%M%S'</span><span class="p">)</span> |
| <span class="k">return</span> <span class="s2">"</span><span class="si">{}</span><span class="s2">_</span><span class="si">{}</span><span class="s2">_</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">dt</span><span class="p">,</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="n">ntpath</span><span class="o">.</span><span class="n">basename</span><span class="p">(</span><span class="n">filename</span><span class="p">))</span></div> |
| |
| <span class="sd">"""</span> |
| <span class="sd"> Upload a local file to a Google Cloud Storage bucket</span> |
| <span class="sd"> """</span> |
| <div class="viewcode-block" id="DataProcPySparkOperator._upload_file_temp"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcPySparkOperator._upload_file_temp">[docs]</a> <span class="k">def</span> <span class="nf">_upload_file_temp</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">bucket</span><span class="p">,</span> <span class="n">local_file</span><span class="p">):</span> |
| <span class="n">temp_filename</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_generate_temp_filename</span><span class="p">(</span><span class="n">local_file</span><span class="p">)</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">bucket</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span> |
| <span class="s2">"If you want Airflow to upload the local file to a temporary bucket, set "</span> |
| <span class="s2">"the 'temp_bucket' key in the connection string"</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Uploading </span><span class="si">%s</span><span class="s2"> to </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">local_file</span><span class="p">,</span> <span class="n">temp_filename</span><span class="p">)</span> |
| |
| <span class="n">GoogleCloudStorageHook</span><span class="p">(</span> |
| <span class="n">google_cloud_storage_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span> |
| <span class="p">)</span><span class="o">.</span><span class="n">upload</span><span class="p">(</span> |
| <span class="n">bucket</span><span class="o">=</span><span class="n">bucket</span><span class="p">,</span> |
| <span class="nb">object</span><span class="o">=</span><span class="n">temp_filename</span><span class="p">,</span> |
| <span class="n">mime_type</span><span class="o">=</span><span class="s1">'application/x-python'</span><span class="p">,</span> |
| <span class="n">filename</span><span class="o">=</span><span class="n">local_file</span> |
| <span class="p">)</span> |
| <span class="k">return</span> <span class="s2">"gs://</span><span class="si">{}</span><span class="s2">/</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">bucket</span><span class="p">,</span> <span class="n">temp_filename</span><span class="p">)</span></div> |
| |
| <span class="nd">@apply_defaults</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">main</span><span class="p">,</span> |
| <span class="n">arguments</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">archives</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">pyfiles</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">files</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">job_name</span><span class="o">=</span><span class="s1">'{{task.task_id}}_{{ds_nodash}}'</span><span class="p">,</span> |
| <span class="n">cluster_name</span><span class="o">=</span><span class="s1">'cluster-1'</span><span class="p">,</span> |
| <span class="n">dataproc_pyspark_properties</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">dataproc_pyspark_jars</span><span class="o">=</span><span class="kc">None</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">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="p">[</span><span class="s1">'ERROR'</span><span class="p">],</span> |
| <span class="o">*</span><span class="n">args</span><span class="p">,</span> |
| <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| |
| <span class="nb">super</span><span class="p">(</span><span class="n">DataProcPySparkOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span> <span class="o">=</span> <span class="n">gcp_conn_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span> <span class="o">=</span> <span class="n">delegate_to</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">main</span> <span class="o">=</span> <span class="n">main</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">arguments</span> <span class="o">=</span> <span class="n">arguments</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">archives</span> <span class="o">=</span> <span class="n">archives</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">files</span> <span class="o">=</span> <span class="n">files</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">pyfiles</span> <span class="o">=</span> <span class="n">pyfiles</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">job_name</span> <span class="o">=</span> <span class="n">job_name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span> <span class="o">=</span> <span class="n">cluster_name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_properties</span> <span class="o">=</span> <span class="n">dataproc_pyspark_properties</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_jars</span> <span class="o">=</span> <span class="n">dataproc_pyspark_jars</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_error_states</span> <span class="o">=</span> <span class="n">job_error_states</span> |
| |
| <div class="viewcode-block" id="DataProcPySparkOperator.execute"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataProcPySparkOperator.execute">[docs]</a> <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> |
| <span class="n">hook</span> <span class="o">=</span> <span class="n">DataProcHook</span><span class="p">(</span> |
| <span class="n">gcp_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span><span class="p">,</span> |
| <span class="n">delegate_to</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span> |
| <span class="p">)</span> |
| <span class="n">job</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">create_job_template</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">task_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">,</span> <span class="s2">"pysparkJob"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_properties</span><span class="p">)</span> |
| |
| <span class="c1"># Check if the file is local, if that is the case, upload it to a bucket</span> |
| <span class="k">if</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">isfile</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">main</span><span class="p">):</span> |
| <span class="n">cluster_info</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">get_cluster</span><span class="p">(</span> |
| <span class="n">project_id</span><span class="o">=</span><span class="n">hook</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">cluster_name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">cluster_name</span> |
| <span class="p">)</span> |
| <span class="n">bucket</span> <span class="o">=</span> <span class="n">cluster_info</span><span class="p">[</span><span class="s1">'config'</span><span class="p">][</span><span class="s1">'configBucket'</span><span class="p">]</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">main</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_upload_file_temp</span><span class="p">(</span><span class="n">bucket</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">main</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">set_python_main</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">main</span><span class="p">)</span> |
| |
| <span class="n">job</span><span class="o">.</span><span class="n">add_args</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">arguments</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_jar_file_uris</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">dataproc_jars</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_archive_uris</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">archives</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_file_uris</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">files</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">add_python_file_uris</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">pyfiles</span><span class="p">)</span> |
| <span class="n">job</span><span class="o">.</span><span class="n">set_job_name</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">job_name</span><span class="p">)</span> |
| |
| <span class="n">job_to_submit</span> <span class="o">=</span> <span class="n">job</span><span class="o">.</span><span class="n">build</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataproc_job_id</span> <span class="o">=</span> <span class="n">job_to_submit</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="n">hook</span><span class="o">.</span><span class="n">submit</span><span class="p">(</span><span class="n">hook</span><span class="o">.</span><span class="n">project_id</span><span class="p">,</span> <span class="n">job_to_submit</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="bp">self</span><span class="o">.</span><span class="n">job_error_states</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="DataprocWorkflowTemplateBaseOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocWorkflowTemplateBaseOperator">[docs]</a><span class="k">class</span> <span class="nc">DataprocWorkflowTemplateBaseOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> |
| <span class="nd">@apply_defaults</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> |
| <span class="n">project_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="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="o">*</span><span class="n">args</span><span class="p">,</span> |
| <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">DataprocWorkflowTemplateBaseOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span> <span class="o">=</span> <span class="n">gcp_conn_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span> <span class="o">=</span> <span class="n">delegate_to</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">hook</span> <span class="o">=</span> <span class="n">DataProcHook</span><span class="p">(</span> |
| <span class="n">gcp_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span><span class="p">,</span> |
| <span class="n">delegate_to</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span><span class="p">,</span> |
| <span class="n">api_version</span><span class="o">=</span><span class="s1">'v1beta2'</span> |
| <span class="p">)</span> |
| |
| <div class="viewcode-block" id="DataprocWorkflowTemplateBaseOperator.execute"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocWorkflowTemplateBaseOperator.execute">[docs]</a> <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">hook</span><span class="o">.</span><span class="n">wait</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">start</span><span class="p">())</span></div> |
| |
| <div class="viewcode-block" id="DataprocWorkflowTemplateBaseOperator.start"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocWorkflowTemplateBaseOperator.start">[docs]</a> <span class="k">def</span> <span class="nf">start</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">'Please start a workflow operation'</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="DataprocWorkflowTemplateInstantiateOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocWorkflowTemplateInstantiateOperator">[docs]</a><span class="k">class</span> <span class="nc">DataprocWorkflowTemplateInstantiateOperator</span><span class="p">(</span><span class="n">DataprocWorkflowTemplateBaseOperator</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Instantiate a WorkflowTemplate on Google Cloud Dataproc. The operator will wait</span> |
| <span class="sd"> until the WorkflowTemplate is finished executing.</span> |
| |
| <span class="sd"> .. seealso::</span> |
| <span class="sd"> Please refer to:</span> |
| <span class="sd"> https://cloud.google.com/dataproc/docs/reference/rest/v1beta2/projects.regions.workflowTemplates/instantiate</span> |
| |
| <span class="sd"> :param template_id: The id of the template. (templated)</span> |
| <span class="sd"> :type template_id: str</span> |
| <span class="sd"> :param project_id: The ID of the google cloud project in which</span> |
| <span class="sd"> the template runs</span> |
| <span class="sd"> :type project_id: str</span> |
| <span class="sd"> :param region: leave as 'global', might become relevant in the future</span> |
| <span class="sd"> :type region: str</span> |
| <span class="sd"> :param gcp_conn_id: The connection ID to use connecting to Google Cloud Platform.</span> |
| <span class="sd"> :type gcp_conn_id: str</span> |
| <span class="sd"> :param delegate_to: The account to impersonate, if any.</span> |
| <span class="sd"> For this to work, the service account making the request must have domain-wide</span> |
| <span class="sd"> delegation enabled.</span> |
| <span class="sd"> :type delegate_to: str</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="DataprocWorkflowTemplateInstantiateOperator.template_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocWorkflowTemplateInstantiateOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'template_id'</span><span class="p">]</span></div> |
| |
| <span class="nd">@apply_defaults</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">template_id</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="p">(</span><span class="nb">super</span><span class="p">(</span><span class="n">DataprocWorkflowTemplateInstantiateOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span> |
| <span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">))</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">template_id</span> <span class="o">=</span> <span class="n">template_id</span> |
| |
| <div class="viewcode-block" id="DataprocWorkflowTemplateInstantiateOperator.start"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocWorkflowTemplateInstantiateOperator.start">[docs]</a> <span class="k">def</span> <span class="nf">start</span><span class="p">(</span><span class="bp">self</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">'Instantiating Template: </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">template_id</span><span class="p">)</span> |
| <span class="k">return</span> <span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">hook</span><span class="o">.</span><span class="n">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">workflowTemplates</span><span class="p">()</span> |
| <span class="o">.</span><span class="n">instantiate</span><span class="p">(</span> |
| <span class="n">name</span><span class="o">=</span><span class="p">(</span><span class="s1">'projects/</span><span class="si">%s</span><span class="s1">/regions/</span><span class="si">%s</span><span class="s1">/workflowTemplates/</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">project_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="bp">self</span><span class="o">.</span><span class="n">template_id</span><span class="p">)),</span> |
| <span class="n">body</span><span class="o">=</span><span class="p">{</span><span class="s1">'instanceId'</span><span class="p">:</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></div></div> |
| <span class="o">.</span><span class="n">execute</span><span class="p">())</span> |
| |
| |
| <div class="viewcode-block" id="DataprocWorkflowTemplateInstantiateInlineOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocWorkflowTemplateInstantiateInlineOperator">[docs]</a><span class="k">class</span> <span class="nc">DataprocWorkflowTemplateInstantiateInlineOperator</span><span class="p">(</span> |
| <span class="n">DataprocWorkflowTemplateBaseOperator</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Instantiate a WorkflowTemplate Inline on Google Cloud Dataproc. The operator will</span> |
| <span class="sd"> wait until the WorkflowTemplate is finished executing.</span> |
| |
| <span class="sd"> .. seealso::</span> |
| <span class="sd"> Please refer to:</span> |
| <span class="sd"> https://cloud.google.com/dataproc/docs/reference/rest/v1beta2/projects.regions.workflowTemplates/instantiateInline</span> |
| |
| <span class="sd"> :param template: The template contents. (templated)</span> |
| <span class="sd"> :type template: map</span> |
| <span class="sd"> :param project_id: The ID of the google cloud project in which</span> |
| <span class="sd"> the template runs</span> |
| <span class="sd"> :type project_id: str</span> |
| <span class="sd"> :param region: leave as 'global', might become relevant in the future</span> |
| <span class="sd"> :type region: str</span> |
| <span class="sd"> :param gcp_conn_id: The connection ID to use connecting to Google Cloud Platform.</span> |
| <span class="sd"> :type gcp_conn_id: str</span> |
| <span class="sd"> :param delegate_to: The account to impersonate, if any.</span> |
| <span class="sd"> For this to work, the service account making the request must have domain-wide</span> |
| <span class="sd"> delegation enabled.</span> |
| <span class="sd"> :type delegate_to: str</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="DataprocWorkflowTemplateInstantiateInlineOperator.template_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocWorkflowTemplateInstantiateInlineOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'template'</span><span class="p">]</span></div> |
| |
| <span class="nd">@apply_defaults</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">template</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="p">(</span><span class="nb">super</span><span class="p">(</span><span class="n">DataprocWorkflowTemplateInstantiateInlineOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span> |
| <span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">))</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">template</span> <span class="o">=</span> <span class="n">template</span> |
| |
| <div class="viewcode-block" id="DataprocWorkflowTemplateInstantiateInlineOperator.start"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataproc_operator/index.html#airflow.contrib.operators.dataproc_operator.DataprocWorkflowTemplateInstantiateInlineOperator.start">[docs]</a> <span class="k">def</span> <span class="nf">start</span><span class="p">(</span><span class="bp">self</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">'Instantiating Inline Template'</span><span class="p">)</span> |
| <span class="k">return</span> <span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">hook</span><span class="o">.</span><span class="n">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">workflowTemplates</span><span class="p">()</span> |
| <span class="o">.</span><span class="n">instantiateInline</span><span class="p">(</span> |
| <span class="n">parent</span><span class="o">=</span><span class="s1">'projects/</span><span class="si">%s</span><span class="s1">/regions/</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">project_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="n">instanceId</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="n">body</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">template</span><span class="p">)</span></div></div> |
| <span class="o">.</span><span class="n">execute</span><span class="p">())</span> |
| </pre></div> |
| |
| </div> |
| |
| </div> |
| <footer> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| |
| </p> |
| </div> |
| Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| |
| |
| |
| |
| |
| </body> |
| </html> |