| |
| |
| <!DOCTYPE html> |
| <!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]--> |
| <!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]--> |
| <head> |
| <meta charset="utf-8"> |
| |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> |
| |
| <title>airflow.contrib.hooks.databricks_hook — Airflow Documentation</title> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <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 src="../../../../_static/js/modernizr.min.js"></script> |
| |
| <script type="application/javascript"> |
| window.ga=window.ga||function(){(ga.q=ga.q||[]).push(arguments)};ga.l=+new Date; |
| ga("create", "UA-140539454-1", "auto"); |
| ga("send", "pageview"); |
| </script> |
| <script async src="https://www.google-analytics.com/analytics.js"></script> |
| </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 role="search"> |
| <form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get"> |
| <input type="text" name="q" placeholder="Search docs" /> |
| <input type="hidden" name="check_keywords" value="yes" /> |
| <input type="hidden" name="area" value="default" /> |
| </form> |
| </div> |
| |
| |
| </div> |
| |
| <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> |
| |
| |
| |
| |
| |
| |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../project.html">Project</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../license.html">License</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../start.html">Quick Start</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../installation.html">Installation</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../tutorial.html">Tutorial</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../howto/index.html">How-to Guides</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../ui.html">UI / Screenshots</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../concepts.html">Concepts</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../profiling.html">Data Profiling</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../cli.html">Command Line Interface</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling & Triggers</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../plugins.html">Plugins</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../security.html">Security</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../timezone.html">Time zones</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../api.html">Experimental Rest API</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../integration.html">Integration</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../lineage.html">Lineage</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../faq.html">FAQ</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../code.html">API Reference</a></li> |
| </ul> |
| |
| |
| |
| </div> |
| </div> |
| </nav> |
| |
| <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> |
| |
| |
| <nav class="wy-nav-top" aria-label="top navigation"> |
| |
| <i data-toggle="wy-nav-top" class="fa fa-bars"></i> |
| <a href="../../../../index.html">Airflow</a> |
| |
| </nav> |
| |
| |
| <div class="wy-nav-content"> |
| |
| <div class="rst-content"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <div role="navigation" aria-label="breadcrumbs navigation"> |
| |
| <ul class="wy-breadcrumbs"> |
| |
| <li><a href="../../../../index.html">Docs</a> »</li> |
| |
| <li><a href="../../../index.html">Module code</a> »</li> |
| |
| <li>airflow.contrib.hooks.databricks_hook</li> |
| |
| |
| <li class="wy-breadcrumbs-aside"> |
| |
| </li> |
| |
| </ul> |
| |
| |
| <hr/> |
| </div> |
| <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> |
| <div itemprop="articleBody"> |
| |
| <h1>Source code for airflow.contrib.hooks.databricks_hook</h1><div class="highlight"><pre> |
| <span></span><span class="c1"># -*- coding: utf-8 -*-</span> |
| <span class="c1">#</span> |
| <span class="c1"># Licensed to the Apache Software Foundation (ASF) under one</span> |
| <span class="c1"># or more contributor license agreements. See the NOTICE file</span> |
| <span class="c1"># distributed with this work for additional information</span> |
| <span class="c1"># regarding copyright ownership. The ASF licenses this file</span> |
| <span class="c1"># to you under the Apache License, Version 2.0 (the</span> |
| <span class="c1"># "License"); you may not use this file except in compliance</span> |
| <span class="c1"># with the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing,</span> |
| <span class="c1"># software distributed under the License is distributed on an</span> |
| <span class="c1"># "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span> |
| <span class="c1"># KIND, either express or implied. See the License for the</span> |
| <span class="c1"># specific language governing permissions and limitations</span> |
| <span class="c1"># under the License.</span> |
| <span class="c1">#</span> |
| <span class="kn">import</span> <span class="nn">requests</span> |
| |
| <span class="kn">from</span> <span class="nn">airflow</span> <span class="k">import</span> <span class="n">__version__</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.hooks.base_hook</span> <span class="k">import</span> <span class="n">BaseHook</span> |
| <span class="kn">from</span> <span class="nn">requests</span> <span class="k">import</span> <span class="n">exceptions</span> <span class="k">as</span> <span class="n">requests_exceptions</span> |
| <span class="kn">from</span> <span class="nn">requests.auth</span> <span class="k">import</span> <span class="n">AuthBase</span> |
| <span class="kn">from</span> <span class="nn">time</span> <span class="k">import</span> <span class="n">sleep</span> |
| |
| <span class="kn">from</span> <span class="nn">airflow.utils.log.logging_mixin</span> <span class="k">import</span> <span class="n">LoggingMixin</span> |
| |
| <span class="k">try</span><span class="p">:</span> |
| <span class="kn">from</span> <span class="nn">urllib</span> <span class="k">import</span> <span class="n">parse</span> <span class="k">as</span> <span class="n">urlparse</span> |
| <span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span> |
| <span class="kn">import</span> <span class="nn">urlparse</span> |
| |
| <span class="n">RESTART_CLUSTER_ENDPOINT</span> <span class="o">=</span> <span class="p">(</span><span class="s2">"POST"</span><span class="p">,</span> <span class="s2">"api/2.0/clusters/restart"</span><span class="p">)</span> |
| <span class="n">START_CLUSTER_ENDPOINT</span> <span class="o">=</span> <span class="p">(</span><span class="s2">"POST"</span><span class="p">,</span> <span class="s2">"api/2.0/clusters/start"</span><span class="p">)</span> |
| <span class="n">TERMINATE_CLUSTER_ENDPOINT</span> <span class="o">=</span> <span class="p">(</span><span class="s2">"POST"</span><span class="p">,</span> <span class="s2">"api/2.0/clusters/delete"</span><span class="p">)</span> |
| |
| <span class="n">SUBMIT_RUN_ENDPOINT</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'POST'</span><span class="p">,</span> <span class="s1">'api/2.0/jobs/runs/submit'</span><span class="p">)</span> |
| <span class="n">GET_RUN_ENDPOINT</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'GET'</span><span class="p">,</span> <span class="s1">'api/2.0/jobs/runs/get'</span><span class="p">)</span> |
| <span class="n">CANCEL_RUN_ENDPOINT</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'POST'</span><span class="p">,</span> <span class="s1">'api/2.0/jobs/runs/cancel'</span><span class="p">)</span> |
| <span class="n">USER_AGENT_HEADER</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'user-agent'</span><span class="p">:</span> <span class="s1">'airflow-</span><span class="si">{v}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">v</span><span class="o">=</span><span class="n">__version__</span><span class="p">)}</span> |
| |
| |
| <div class="viewcode-block" id="DatabricksHook"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.hooks.databricks_hook.DatabricksHook">[docs]</a><span class="k">class</span> <span class="nc">DatabricksHook</span><span class="p">(</span><span class="n">BaseHook</span><span class="p">,</span> <span class="n">LoggingMixin</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Interact with Databricks.</span> |
| <span class="sd"> """</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">databricks_conn_id</span><span class="o">=</span><span class="s1">'databricks_default'</span><span class="p">,</span> |
| <span class="n">timeout_seconds</span><span class="o">=</span><span class="mi">180</span><span class="p">,</span> |
| <span class="n">retry_limit</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span> |
| <span class="n">retry_delay</span><span class="o">=</span><span class="mf">1.0</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :param databricks_conn_id: The name of the databricks connection to use.</span> |
| <span class="sd"> :type databricks_conn_id: string</span> |
| <span class="sd"> :param timeout_seconds: The amount of time in seconds the requests library</span> |
| <span class="sd"> will wait before timing-out.</span> |
| <span class="sd"> :type timeout_seconds: int</span> |
| <span class="sd"> :param retry_limit: The number of times to retry the connection in case of</span> |
| <span class="sd"> service outages.</span> |
| <span class="sd"> :type retry_limit: int</span> |
| <span class="sd"> :param retry_delay: The number of seconds to wait between retries (it</span> |
| <span class="sd"> might be a floating point number).</span> |
| <span class="sd"> :type retry_delay: float</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">databricks_conn_id</span> <span class="o">=</span> <span class="n">databricks_conn_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">databricks_conn</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_connection</span><span class="p">(</span><span class="n">databricks_conn_id</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">timeout_seconds</span> <span class="o">=</span> <span class="n">timeout_seconds</span> |
| <span class="k">if</span> <span class="n">retry_limit</span> <span class="o"><</span> <span class="mi">1</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Retry limit must be greater than equal to 1'</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">retry_limit</span> <span class="o">=</span> <span class="n">retry_limit</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">retry_delay</span> <span class="o">=</span> <span class="n">retry_delay</span> |
| |
| <span class="k">def</span> <span class="nf">_parse_host</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">host</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> The purpose of this function is to be robust to improper connections</span> |
| <span class="sd"> settings provided by users, specifically in the host field.</span> |
| |
| |
| <span class="sd"> For example -- when users supply ``https://xx.cloud.databricks.com`` as the</span> |
| <span class="sd"> host, we must strip out the protocol to get the host.</span> |
| <span class="sd"> >>> h = DatabricksHook()</span> |
| <span class="sd"> >>> assert h._parse_host('https://xx.cloud.databricks.com') == \</span> |
| <span class="sd"> 'xx.cloud.databricks.com'</span> |
| |
| <span class="sd"> In the case where users supply the correct ``xx.cloud.databricks.com`` as the</span> |
| <span class="sd"> host, this function is a no-op.</span> |
| <span class="sd"> >>> assert h._parse_host('xx.cloud.databricks.com') == 'xx.cloud.databricks.com'</span> |
| <span class="sd"> """</span> |
| <span class="n">urlparse_host</span> <span class="o">=</span> <span class="n">urlparse</span><span class="o">.</span><span class="n">urlparse</span><span class="p">(</span><span class="n">host</span><span class="p">)</span><span class="o">.</span><span class="n">hostname</span> |
| <span class="k">if</span> <span class="n">urlparse_host</span><span class="p">:</span> |
| <span class="c1"># In this case, host = https://xx.cloud.databricks.com</span> |
| <span class="k">return</span> <span class="n">urlparse_host</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="c1"># In this case, host = xx.cloud.databricks.com</span> |
| <span class="k">return</span> <span class="n">host</span> |
| |
| <span class="k">def</span> <span class="nf">_do_api_call</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">endpoint_info</span><span class="p">,</span> <span class="n">json</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Utility function to perform an API call with retries</span> |
| <span class="sd"> :param endpoint_info: Tuple of method and endpoint</span> |
| <span class="sd"> :type endpoint_info: (string, string)</span> |
| <span class="sd"> :param json: Parameters for this API call.</span> |
| <span class="sd"> :type json: dict</span> |
| <span class="sd"> :return: If the api call returns a OK status code,</span> |
| <span class="sd"> this function returns the response in JSON. Otherwise,</span> |
| <span class="sd"> we throw an AirflowException.</span> |
| <span class="sd"> :rtype: dict</span> |
| <span class="sd"> """</span> |
| <span class="n">method</span><span class="p">,</span> <span class="n">endpoint</span> <span class="o">=</span> <span class="n">endpoint_info</span> |
| <span class="n">url</span> <span class="o">=</span> <span class="s1">'https://</span><span class="si">{host}</span><span class="s1">/</span><span class="si">{endpoint}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span> |
| <span class="n">host</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_parse_host</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">databricks_conn</span><span class="o">.</span><span class="n">host</span><span class="p">),</span> |
| <span class="n">endpoint</span><span class="o">=</span><span class="n">endpoint</span><span class="p">)</span> |
| <span class="k">if</span> <span class="s1">'token'</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">databricks_conn</span><span class="o">.</span><span class="n">extra_dejson</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">'Using token auth.'</span><span class="p">)</span> |
| <span class="n">auth</span> <span class="o">=</span> <span class="n">_TokenAuth</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">databricks_conn</span><span class="o">.</span><span class="n">extra_dejson</span><span class="p">[</span><span class="s1">'token'</span><span class="p">])</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Using basic auth.'</span><span class="p">)</span> |
| <span class="n">auth</span> <span class="o">=</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">databricks_conn</span><span class="o">.</span><span class="n">login</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">databricks_conn</span><span class="o">.</span><span class="n">password</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">method</span> <span class="o">==</span> <span class="s1">'GET'</span><span class="p">:</span> |
| <span class="n">request_func</span> <span class="o">=</span> <span class="n">requests</span><span class="o">.</span><span class="n">get</span> |
| <span class="k">elif</span> <span class="n">method</span> <span class="o">==</span> <span class="s1">'POST'</span><span class="p">:</span> |
| <span class="n">request_func</span> <span class="o">=</span> <span class="n">requests</span><span class="o">.</span><span class="n">post</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">'Unexpected HTTP Method: '</span> <span class="o">+</span> <span class="n">method</span><span class="p">)</span> |
| |
| <span class="n">attempt_num</span> <span class="o">=</span> <span class="mi">1</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">request_func</span><span class="p">(</span> |
| <span class="n">url</span><span class="p">,</span> |
| <span class="n">json</span><span class="o">=</span><span class="n">json</span><span class="p">,</span> |
| <span class="n">auth</span><span class="o">=</span><span class="n">auth</span><span class="p">,</span> |
| <span class="n">headers</span><span class="o">=</span><span class="n">USER_AGENT_HEADER</span><span class="p">,</span> |
| <span class="n">timeout</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">timeout_seconds</span><span class="p">)</span> |
| <span class="n">response</span><span class="o">.</span><span class="n">raise_for_status</span><span class="p">()</span> |
| <span class="k">return</span> <span class="n">response</span><span class="o">.</span><span class="n">json</span><span class="p">()</span> |
| <span class="k">except</span> <span class="n">requests_exceptions</span><span class="o">.</span><span class="n">RequestException</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">_retryable_error</span><span class="p">(</span><span class="n">e</span><span class="p">):</span> |
| <span class="c1"># In this case, the user probably made a mistake.</span> |
| <span class="c1"># Don't retry.</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">'Response: </span><span class="si">{0}</span><span class="s1">, Status Code: </span><span class="si">{1}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span> |
| <span class="n">e</span><span class="o">.</span><span class="n">response</span><span class="o">.</span><span class="n">content</span><span class="p">,</span> <span class="n">e</span><span class="o">.</span><span class="n">response</span><span class="o">.</span><span class="n">status_code</span><span class="p">))</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_log_request_error</span><span class="p">(</span><span class="n">attempt_num</span><span class="p">,</span> <span class="n">e</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">attempt_num</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">retry_limit</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">((</span><span class="s1">'API requests to Databricks failed </span><span class="si">{}</span><span class="s1"> times. '</span> <span class="o">+</span> |
| <span class="s1">'Giving up.'</span><span class="p">)</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">retry_limit</span><span class="p">))</span> |
| |
| <span class="n">attempt_num</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="n">sleep</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">retry_delay</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_log_request_error</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">attempt_num</span><span class="p">,</span> <span class="n">error</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">error</span><span class="p">(</span> |
| <span class="s1">'Attempt </span><span class="si">%s</span><span class="s1"> API Request to Databricks failed with reason: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> |
| <span class="n">attempt_num</span><span class="p">,</span> <span class="n">error</span> |
| <span class="p">)</span> |
| |
| <div class="viewcode-block" id="DatabricksHook.submit_run"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.hooks.databricks_hook.DatabricksHook.submit_run">[docs]</a> <span class="k">def</span> <span class="nf">submit_run</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">json</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Utility function to call the ``api/2.0/jobs/runs/submit`` endpoint.</span> |
| |
| <span class="sd"> :param json: The data used in the body of the request to the ``submit`` endpoint.</span> |
| <span class="sd"> :type json: dict</span> |
| <span class="sd"> :return: the run_id as a string</span> |
| <span class="sd"> :rtype: string</span> |
| <span class="sd"> """</span> |
| <span class="n">response</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_do_api_call</span><span class="p">(</span><span class="n">SUBMIT_RUN_ENDPOINT</span><span class="p">,</span> <span class="n">json</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">response</span><span class="p">[</span><span class="s1">'run_id'</span><span class="p">]</span></div> |
| |
| <span class="k">def</span> <span class="nf">get_run_page_url</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">run_id</span><span class="p">):</span> |
| <span class="n">json</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'run_id'</span><span class="p">:</span> <span class="n">run_id</span><span class="p">}</span> |
| <span class="n">response</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_do_api_call</span><span class="p">(</span><span class="n">GET_RUN_ENDPOINT</span><span class="p">,</span> <span class="n">json</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">response</span><span class="p">[</span><span class="s1">'run_page_url'</span><span class="p">]</span> |
| |
| <span class="k">def</span> <span class="nf">get_run_state</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">run_id</span><span class="p">):</span> |
| <span class="n">json</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'run_id'</span><span class="p">:</span> <span class="n">run_id</span><span class="p">}</span> |
| <span class="n">response</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_do_api_call</span><span class="p">(</span><span class="n">GET_RUN_ENDPOINT</span><span class="p">,</span> <span class="n">json</span><span class="p">)</span> |
| <span class="n">state</span> <span class="o">=</span> <span class="n">response</span><span class="p">[</span><span class="s1">'state'</span><span class="p">]</span> |
| <span class="n">life_cycle_state</span> <span class="o">=</span> <span class="n">state</span><span class="p">[</span><span class="s1">'life_cycle_state'</span><span class="p">]</span> |
| <span class="c1"># result_state may not be in the state if not terminal</span> |
| <span class="n">result_state</span> <span class="o">=</span> <span class="n">state</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'result_state'</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="n">state_message</span> <span class="o">=</span> <span class="n">state</span><span class="p">[</span><span class="s1">'state_message'</span><span class="p">]</span> |
| <span class="k">return</span> <span class="n">RunState</span><span class="p">(</span><span class="n">life_cycle_state</span><span class="p">,</span> <span class="n">result_state</span><span class="p">,</span> <span class="n">state_message</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">cancel_run</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">run_id</span><span class="p">):</span> |
| <span class="n">json</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'run_id'</span><span class="p">:</span> <span class="n">run_id</span><span class="p">}</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_do_api_call</span><span class="p">(</span><span class="n">CANCEL_RUN_ENDPOINT</span><span class="p">,</span> <span class="n">json</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">restart_cluster</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">json</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_do_api_call</span><span class="p">(</span><span class="n">RESTART_CLUSTER_ENDPOINT</span><span class="p">,</span> <span class="n">json</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">start_cluster</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">json</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_do_api_call</span><span class="p">(</span><span class="n">START_CLUSTER_ENDPOINT</span><span class="p">,</span> <span class="n">json</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">terminate_cluster</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">json</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_do_api_call</span><span class="p">(</span><span class="n">TERMINATE_CLUSTER_ENDPOINT</span><span class="p">,</span> <span class="n">json</span><span class="p">)</span></div> |
| |
| |
| <span class="k">def</span> <span class="nf">_retryable_error</span><span class="p">(</span><span class="n">exception</span><span class="p">):</span> |
| <span class="k">return</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">exception</span><span class="p">,</span> <span class="n">requests_exceptions</span><span class="o">.</span><span class="n">ConnectionError</span><span class="p">)</span> \ |
| <span class="ow">or</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">exception</span><span class="p">,</span> <span class="n">requests_exceptions</span><span class="o">.</span><span class="n">Timeout</span><span class="p">)</span> \ |
| <span class="ow">or</span> <span class="n">exception</span><span class="o">.</span><span class="n">response</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">exception</span><span class="o">.</span><span class="n">response</span><span class="o">.</span><span class="n">status_code</span> <span class="o">>=</span> <span class="mi">500</span> |
| |
| |
| <span class="n">RUN_LIFE_CYCLE_STATES</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="s1">'PENDING'</span><span class="p">,</span> |
| <span class="s1">'RUNNING'</span><span class="p">,</span> |
| <span class="s1">'TERMINATING'</span><span class="p">,</span> |
| <span class="s1">'TERMINATED'</span><span class="p">,</span> |
| <span class="s1">'SKIPPED'</span><span class="p">,</span> |
| <span class="s1">'INTERNAL_ERROR'</span> |
| <span class="p">]</span> |
| |
| |
| <span class="k">class</span> <span class="nc">RunState</span><span class="p">:</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Utility class for the run state concept of Databricks runs.</span> |
| <span class="sd"> """</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">life_cycle_state</span><span class="p">,</span> <span class="n">result_state</span><span class="p">,</span> <span class="n">state_message</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">life_cycle_state</span> <span class="o">=</span> <span class="n">life_cycle_state</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">result_state</span> <span class="o">=</span> <span class="n">result_state</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">state_message</span> <span class="o">=</span> <span class="n">state_message</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">is_terminal</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">life_cycle_state</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">RUN_LIFE_CYCLE_STATES</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span> |
| <span class="p">(</span><span class="s1">'Unexpected life cycle state: </span><span class="si">{}</span><span class="s1">: If the state has '</span> |
| <span class="s1">'been introduced recently, please check the Databricks user '</span> |
| <span class="s1">'guide for troubleshooting information'</span><span class="p">)</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">life_cycle_state</span><span class="p">))</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">life_cycle_state</span> <span class="ow">in</span> <span class="p">(</span><span class="s1">'TERMINATED'</span><span class="p">,</span> <span class="s1">'SKIPPED'</span><span class="p">,</span> <span class="s1">'INTERNAL_ERROR'</span><span class="p">)</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">is_successful</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">result_state</span> <span class="o">==</span> <span class="s1">'SUCCESS'</span> |
| |
| <span class="k">def</span> <span class="nf">__eq__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">other</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">life_cycle_state</span> <span class="o">==</span> <span class="n">other</span><span class="o">.</span><span class="n">life_cycle_state</span> <span class="ow">and</span> \ |
| <span class="bp">self</span><span class="o">.</span><span class="n">result_state</span> <span class="o">==</span> <span class="n">other</span><span class="o">.</span><span class="n">result_state</span> <span class="ow">and</span> \ |
| <span class="bp">self</span><span class="o">.</span><span class="n">state_message</span> <span class="o">==</span> <span class="n">other</span><span class="o">.</span><span class="n">state_message</span> |
| |
| <span class="k">def</span> <span class="nf">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="vm">__dict__</span><span class="p">)</span> |
| |
| |
| <span class="k">class</span> <span class="nc">_TokenAuth</span><span class="p">(</span><span class="n">AuthBase</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Helper class for requests Auth field. AuthBase requires you to implement the __call__</span> |
| <span class="sd"> magic function.</span> |
| <span class="sd"> """</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">token</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">token</span> <span class="o">=</span> <span class="n">token</span> |
| |
| <span class="k">def</span> <span class="nf">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">r</span><span class="p">):</span> |
| <span class="n">r</span><span class="o">.</span><span class="n">headers</span><span class="p">[</span><span class="s1">'Authorization'</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'Bearer '</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">token</span> |
| <span class="k">return</span> <span class="n">r</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" 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/js/theme.js"></script> |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| </body> |
| </html> |