You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@airflow.apache.org by ka...@apache.org on 2018/08/27 16:27:06 UTC
[46/51] [partial] incubator-airflow-site git commit: 1.10.0
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/11437c14/_modules/airflow/contrib/hooks/gcp_api_base_hook.html
----------------------------------------------------------------------
diff --git a/_modules/airflow/contrib/hooks/gcp_api_base_hook.html b/_modules/airflow/contrib/hooks/gcp_api_base_hook.html
new file mode 100644
index 0000000..c81584e
--- /dev/null
+++ b/_modules/airflow/contrib/hooks/gcp_api_base_hook.html
@@ -0,0 +1,379 @@
+
+
+<!DOCTYPE html>
+<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
+<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
+<head>
+ <meta charset="utf-8">
+
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
+
+ <title>airflow.contrib.hooks.gcp_api_base_hook — Airflow Documentation</title>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
+
+
+
+
+
+ <link rel="index" title="Index"
+ href="../../../../genindex.html"/>
+ <link rel="search" title="Search" href="../../../../search.html"/>
+ <link rel="top" title="Airflow Documentation" href="../../../../index.html"/>
+ <link rel="up" title="Module code" href="../../../index.html"/>
+
+
+ <script src="../../../../_static/js/modernizr.min.js"></script>
+
+</head>
+
+<body class="wy-body-for-nav" role="document">
+
+
+ <div class="wy-grid-for-nav">
+
+
+ <nav data-toggle="wy-nav-shift" class="wy-nav-side">
+ <div class="wy-side-scroll">
+ <div class="wy-side-nav-search">
+
+
+
+ <a href="../../../../index.html" class="icon icon-home"> Airflow
+
+
+
+ </a>
+
+
+
+
+
+
+
+<div role="search">
+ <form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get">
+ <input type="text" name="q" placeholder="Search docs" />
+ <input type="hidden" name="check_keywords" value="yes" />
+ <input type="hidden" name="area" value="default" />
+ </form>
+</div>
+
+
+ </div>
+
+ <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
+
+
+
+
+
+
+ <ul>
+<li class="toctree-l1"><a class="reference internal" href="../../../../project.html">Project</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../license.html">License</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../start.html">Quick Start</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../installation.html">Installation</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../tutorial.html">Tutorial</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../howto/index.html">How-to Guides</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../ui.html">UI / Screenshots</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../concepts.html">Concepts</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../profiling.html">Data Profiling</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../cli.html">Command Line Interface</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling & Triggers</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../plugins.html">Plugins</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../security.html">Security</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../timezone.html">Time zones</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../api.html">Experimental Rest API</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../integration.html">Integration</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../lineage.html">Lineage</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../faq.html">FAQ</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../code.html">API Reference</a></li>
+</ul>
+
+
+
+ </div>
+ </div>
+ </nav>
+
+ <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
+
+
+ <nav class="wy-nav-top" role="navigation" aria-label="top navigation">
+
+ <i data-toggle="wy-nav-top" class="fa fa-bars"></i>
+ <a href="../../../../index.html">Airflow</a>
+
+ </nav>
+
+
+
+ <div class="wy-nav-content">
+ <div class="rst-content">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+<div role="navigation" aria-label="breadcrumbs navigation">
+
+ <ul class="wy-breadcrumbs">
+
+ <li><a href="../../../../index.html">Docs</a> »</li>
+
+ <li><a href="../../../index.html">Module code</a> »</li>
+
+ <li>airflow.contrib.hooks.gcp_api_base_hook</li>
+
+
+ <li class="wy-breadcrumbs-aside">
+
+
+
+ </li>
+
+ </ul>
+
+
+ <hr/>
+</div>
+ <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
+ <div itemprop="articleBody">
+
+ <h1>Source code for airflow.contrib.hooks.gcp_api_base_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">json</span>
+
+<span class="kn">import</span> <span class="nn">httplib2</span>
+<span class="kn">from</span> <span class="nn">oauth2client.client</span> <span class="k">import</span> <span class="n">GoogleCredentials</span>
+<span class="kn">from</span> <span class="nn">oauth2client.service_account</span> <span class="k">import</span> <span class="n">ServiceAccountCredentials</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">airflow.utils.log.logging_mixin</span> <span class="k">import</span> <span class="n">LoggingMixin</span>
+
+
+<div class="viewcode-block" id="GoogleCloudBaseHook"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.hooks.gcp_api_base_hook.GoogleCloudBaseHook">[docs]</a><span class="k">class</span> <span class="nc">GoogleCloudBaseHook</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"> A base hook for Google cloud-related hooks. Google cloud has a shared REST</span>
+<span class="sd"> API client that is built in the same way no matter which service you use.</span>
+<span class="sd"> This class helps construct and authorize the credentials needed to then</span>
+<span class="sd"> call apiclient.discovery.build() to actually discover and build a client</span>
+<span class="sd"> for a Google cloud service.</span>
+
+<span class="sd"> The class also contains some miscellaneous helper functions.</span>
+
+<span class="sd"> All hook derived from this base hook use the 'Google Cloud Platform' connection</span>
+<span class="sd"> type. Two ways of authentication are supported:</span>
+
+<span class="sd"> Default credentials: Only specify 'Project Id'. Then you need to have executed</span>
+<span class="sd"> ``gcloud auth`` on the Airflow worker machine.</span>
+
+<span class="sd"> JSON key file: Specify 'Project Id', 'Key Path' and 'Scope'.</span>
+
+<span class="sd"> Legacy P12 key files are not supported.</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">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="sd">"""</span>
+<span class="sd"> :param gcp_conn_id: The connection ID to use when fetching connection info.</span>
+<span class="sd"> :type gcp_conn_id: string</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: string</span>
+<span class="sd"> """</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">extras</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="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">extra_dejson</span>
+
+ <span class="k">def</span> <span class="nf">_get_credentials</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Returns the Credentials object for Google API</span>
+<span class="sd"> """</span>
+ <span class="n">key_path</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_field</span><span class="p">(</span><span class="s1">'key_path'</span><span class="p">,</span> <span class="kc">False</span><span class="p">)</span>
+ <span class="n">keyfile_dict</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_field</span><span class="p">(</span><span class="s1">'keyfile_dict'</span><span class="p">,</span> <span class="kc">False</span><span class="p">)</span>
+ <span class="n">scope</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_field</span><span class="p">(</span><span class="s1">'scope'</span><span class="p">,</span> <span class="kc">False</span><span class="p">)</span>
+
+ <span class="k">if</span> <span class="ow">not</span> <span class="n">key_path</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">keyfile_dict</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">'Getting connection using `gcloud auth` user, '</span>
+ <span class="s1">'since no key file is defined for hook.'</span><span class="p">)</span>
+ <span class="n">credentials</span> <span class="o">=</span> <span class="n">GoogleCredentials</span><span class="o">.</span><span class="n">get_application_default</span><span class="p">()</span>
+ <span class="k">elif</span> <span class="n">key_path</span><span class="p">:</span>
+ <span class="k">if</span> <span class="ow">not</span> <span class="n">scope</span><span class="p">:</span>
+ <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">'Scope should be defined when using a key file.'</span><span class="p">)</span>
+ <span class="n">scopes</span> <span class="o">=</span> <span class="p">[</span><span class="n">s</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span> <span class="k">for</span> <span class="n">s</span> <span class="ow">in</span> <span class="n">scope</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">','</span><span class="p">)]</span>
+
+ <span class="c1"># Get credentials from a JSON file.</span>
+ <span class="k">if</span> <span class="n">key_path</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'.json'</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">'Getting connection using a JSON key file.'</span><span class="p">)</span>
+ <span class="n">credentials</span> <span class="o">=</span> <span class="n">ServiceAccountCredentials</span> \
+ <span class="o">.</span><span class="n">from_json_keyfile_name</span><span class="p">(</span><span class="n">key_path</span><span class="p">,</span> <span class="n">scopes</span><span class="p">)</span>
+ <span class="k">elif</span> <span class="n">key_path</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'.p12'</span><span class="p">):</span>
+ <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">'Legacy P12 key file are not supported, '</span>
+ <span class="s1">'use a JSON key file.'</span><span class="p">)</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">'Unrecognised extension for key file.'</span><span class="p">)</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="k">if</span> <span class="ow">not</span> <span class="n">scope</span><span class="p">:</span>
+ <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">'Scope should be defined when using key JSON.'</span><span class="p">)</span>
+ <span class="n">scopes</span> <span class="o">=</span> <span class="p">[</span><span class="n">s</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span> <span class="k">for</span> <span class="n">s</span> <span class="ow">in</span> <span class="n">scope</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">','</span><span class="p">)]</span>
+
+ <span class="c1"># Get credentials from JSON data provided in the UI.</span>
+ <span class="k">try</span><span class="p">:</span>
+ <span class="n">keyfile_dict</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">loads</span><span class="p">(</span><span class="n">keyfile_dict</span><span class="p">)</span>
+
+ <span class="c1"># Depending on how the JSON was formatted, it may contain</span>
+ <span class="c1"># escaped newlines. Convert those to actual newlines.</span>
+ <span class="n">keyfile_dict</span><span class="p">[</span><span class="s1">'private_key'</span><span class="p">]</span> <span class="o">=</span> <span class="n">keyfile_dict</span><span class="p">[</span><span class="s1">'private_key'</span><span class="p">]</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span>
+ <span class="s1">'</span><span class="se">\\</span><span class="s1">n'</span><span class="p">,</span> <span class="s1">'</span><span class="se">\n</span><span class="s1">'</span><span class="p">)</span>
+
+ <span class="n">credentials</span> <span class="o">=</span> <span class="n">ServiceAccountCredentials</span> \
+ <span class="o">.</span><span class="n">from_json_keyfile_dict</span><span class="p">(</span><span class="n">keyfile_dict</span><span class="p">,</span> <span class="n">scopes</span><span class="p">)</span>
+ <span class="k">except</span> <span class="n">json</span><span class="o">.</span><span class="n">decoder</span><span class="o">.</span><span class="n">JSONDecodeError</span><span class="p">:</span>
+ <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">'Invalid key JSON.'</span><span class="p">)</span>
+
+ <span class="k">return</span> <span class="n">credentials</span><span class="o">.</span><span class="n">create_delegated</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span><span class="p">)</span> \
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span> <span class="k">else</span> <span class="n">credentials</span>
+
+ <span class="k">def</span> <span class="nf">_get_access_token</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Returns a valid access token from Google API Credentials</span>
+<span class="sd"> """</span>
+ <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_credentials</span><span class="p">()</span><span class="o">.</span><span class="n">get_access_token</span><span class="p">()</span><span class="o">.</span><span class="n">access_token</span>
+
+ <span class="k">def</span> <span class="nf">_authorize</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Returns an authorized HTTP object to be used to build a Google cloud</span>
+<span class="sd"> service hook connection.</span>
+<span class="sd"> """</span>
+ <span class="n">credentials</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_credentials</span><span class="p">()</span>
+ <span class="n">http</span> <span class="o">=</span> <span class="n">httplib2</span><span class="o">.</span><span class="n">Http</span><span class="p">()</span>
+ <span class="k">return</span> <span class="n">credentials</span><span class="o">.</span><span class="n">authorize</span><span class="p">(</span><span class="n">http</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">_get_field</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">f</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Fetches a field from extras, and returns it. This is some Airflow</span>
+<span class="sd"> magic. The google_cloud_platform hook type adds custom UI elements</span>
+<span class="sd"> to the hook page, which allow admins to specify service_account,</span>
+<span class="sd"> key_path, etc. They get formatted as shown below.</span>
+<span class="sd"> """</span>
+ <span class="n">long_f</span> <span class="o">=</span> <span class="s1">'extra__google_cloud_platform__</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">f</span><span class="p">)</span>
+ <span class="k">if</span> <span class="n">long_f</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">extras</span><span class="p">:</span>
+ <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">extras</span><span class="p">[</span><span class="n">long_f</span><span class="p">]</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="k">return</span> <span class="n">default</span>
+
+ <span class="nd">@property</span>
+ <span class="k">def</span> <span class="nf">project_id</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">_get_field</span><span class="p">(</span><span class="s1">'project'</span><span class="p">)</span></div>
+</pre></div>
+
+ </div>
+ <div class="articleComments">
+
+ </div>
+ </div>
+ <footer>
+
+
+ <hr/>
+
+ <div role="contentinfo">
+ <p>
+
+ </p>
+ </div>
+ Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
+
+</footer>
+
+ </div>
+ </div>
+
+ </section>
+
+ </div>
+
+
+
+
+
+ <script type="text/javascript">
+ var DOCUMENTATION_OPTIONS = {
+ URL_ROOT:'../../../../',
+ VERSION:'',
+ COLLAPSE_INDEX:false,
+ FILE_SUFFIX:'.html',
+ HAS_SOURCE: true,
+ SOURCELINK_SUFFIX: '.txt'
+ };
+ </script>
+ <script type="text/javascript" src="../../../../_static/jquery.js"></script>
+ <script type="text/javascript" src="../../../../_static/underscore.js"></script>
+ <script type="text/javascript" src="../../../../_static/doctools.js"></script>
+
+
+
+
+
+ <script type="text/javascript" src="../../../../_static/js/theme.js"></script>
+
+
+
+
+ <script type="text/javascript">
+ jQuery(function () {
+ SphinxRtdTheme.StickyNav.enable();
+ });
+ </script>
+
+
+</body>
+</html>
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/11437c14/_modules/airflow/contrib/hooks/gcp_dataflow_hook.html
----------------------------------------------------------------------
diff --git a/_modules/airflow/contrib/hooks/gcp_dataflow_hook.html b/_modules/airflow/contrib/hooks/gcp_dataflow_hook.html
index 82e3ccd..ce6f6ff 100644
--- a/_modules/airflow/contrib/hooks/gcp_dataflow_hook.html
+++ b/_modules/airflow/contrib/hooks/gcp_dataflow_hook.html
@@ -91,7 +91,7 @@
<li class="toctree-l1"><a class="reference internal" href="../../../../start.html">Quick Start</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../installation.html">Installation</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../tutorial.html">Tutorial</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../../../configuration.html">Configuration</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../howto/index.html">How-to Guides</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../ui.html">UI / Screenshots</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../concepts.html">Concepts</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../profiling.html">Data Profiling</a></li>
@@ -99,8 +99,10 @@
<li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling & Triggers</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../plugins.html">Plugins</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../security.html">Security</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../timezone.html">Time zones</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../api.html">Experimental Rest API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../integration.html">Integration</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../lineage.html">Lineage</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../faq.html">FAQ</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../code.html">API Reference</a></li>
</ul>
@@ -169,17 +171,23 @@
<h1>Source code for airflow.contrib.hooks.gcp_dataflow_hook</h1><div class="highlight"><pre>
<span></span><span class="c1"># -*- coding: utf-8 -*-</span>
<span class="c1">#</span>
-<span class="c1"># Licensed under the Apache License, Version 2.0 (the "License");</span>
-<span class="c1"># you may not use this file except in compliance with the License.</span>
-<span class="c1"># 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, software</span>
-<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span>
-<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
-<span class="c1"># See the License for the specific language governing permissions and</span>
-<span class="c1"># limitations under the License.</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="kn">import</span> <span class="nn">json</span>
<span class="kn">import</span> <span class="nn">select</span>
<span class="kn">import</span> <span class="nn">subprocess</span>
<span class="kn">import</span> <span class="nn">time</span>
@@ -190,18 +198,25 @@
<span class="kn">from</span> <span class="nn">airflow.contrib.hooks.gcp_api_base_hook</span> <span class="k">import</span> <span class="n">GoogleCloudBaseHook</span>
<span class="kn">from</span> <span class="nn">airflow.utils.log.logging_mixin</span> <span class="k">import</span> <span class="n">LoggingMixin</span>
+<span class="c1"># This is the default location</span>
+<span class="c1"># https://cloud.google.com/dataflow/pipelines/specifying-exec-params</span>
+<span class="n">DEFAULT_DATAFLOW_LOCATION</span> <span class="o">=</span> <span class="s1">'us-central1'</span>
+
<span class="k">class</span> <span class="nc">_DataflowJob</span><span class="p">(</span><span class="n">LoggingMixin</span><span class="p">):</span>
- <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataflow</span><span class="p">,</span> <span class="n">project_number</span><span class="p">,</span> <span class="n">name</span><span class="p">):</span>
+ <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataflow</span><span class="p">,</span> <span class="n">project_number</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">location</span><span class="p">,</span> <span class="n">poll_sleep</span><span class="o">=</span><span class="mi">10</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_dataflow</span> <span class="o">=</span> <span class="n">dataflow</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_project_number</span> <span class="o">=</span> <span class="n">project_number</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_job_name</span> <span class="o">=</span> <span class="n">name</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_job_location</span> <span class="o">=</span> <span class="n">location</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_job_id</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_job</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_job</span><span class="p">()</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_poll_sleep</span> <span class="o">=</span> <span class="n">poll_sleep</span>
<span class="k">def</span> <span class="nf">_get_job_id_from_name</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
- <span class="n">jobs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dataflow</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">jobs</span><span class="p">()</span><span class="o">.</span><span class="n">list</span><span class="p">(</span>
- <span class="n">projectId</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_project_number</span>
+ <span class="n">jobs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dataflow</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">locations</span><span class="p">()</span><span class="o">.</span><span class="n">jobs</span><span class="p">()</span><span class="o">.</span><span class="n">list</span><span class="p">(</span>
+ <span class="n">projectId</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_project_number</span><span class="p">,</span>
+ <span class="n">location</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_job_location</span>
<span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">()</span>
<span class="k">for</span> <span class="n">job</span> <span class="ow">in</span> <span class="n">jobs</span><span class="p">[</span><span class="s1">'jobs'</span><span class="p">]:</span>
<span class="k">if</span> <span class="n">job</span><span class="p">[</span><span class="s1">'name'</span><span class="p">]</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job_name</span><span class="p">:</span>
@@ -210,28 +225,39 @@
<span class="k">return</span> <span class="kc">None</span>
<span class="k">def</span> <span class="nf">_get_job</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
- <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job_id</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job_name</span><span class="p">:</span>
<span class="n">job</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_job_id_from_name</span><span class="p">()</span>
<span class="k">else</span><span class="p">:</span>
- <span class="n">job</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dataflow</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">jobs</span><span class="p">()</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">projectId</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_project_number</span><span class="p">,</span>
- <span class="n">jobId</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_job_id</span><span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">()</span>
- <span class="k">if</span> <span class="s1">'currentState'</span> <span class="ow">in</span> <span class="n">job</span><span class="p">:</span>
+ <span class="n">job</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dataflow</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">jobs</span><span class="p">()</span><span class="o">.</span><span class="n">get</span><span class="p">(</span>
+ <span class="n">projectId</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_project_number</span><span class="p">,</span>
+ <span class="n">jobId</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_job_id</span>
+ <span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">()</span>
+
+ <span class="k">if</span> <span class="n">job</span> <span class="ow">and</span> <span class="s1">'currentState'</span> <span class="ow">in</span> <span class="n">job</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span>
<span class="s1">'Google Cloud DataFlow job </span><span class="si">%s</span><span class="s1"> is </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span>
<span class="n">job</span><span class="p">[</span><span class="s1">'name'</span><span class="p">],</span> <span class="n">job</span><span class="p">[</span><span class="s1">'currentState'</span><span class="p">]</span>
<span class="p">)</span>
- <span class="k">else</span><span class="p">:</span>
+ <span class="k">elif</span> <span class="n">job</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span>
<span class="s1">'Google Cloud DataFlow with job_id </span><span class="si">%s</span><span class="s1"> has name </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_job_id</span><span class="p">,</span> <span class="n">job</span><span class="p">[</span><span class="s1">'name'</span><span class="p">]</span>
<span class="p">)</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span>
+ <span class="s1">'Google Cloud DataFlow job not available yet..'</span>
+ <span class="p">)</span>
+
<span class="k">return</span> <span class="n">job</span>
<span class="k">def</span> <span class="nf">wait_for_done</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">while</span> <span class="kc">True</span><span class="p">:</span>
- <span class="k">if</span> <span class="s1">'currentState'</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job</span><span class="p">:</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job</span> <span class="ow">and</span> <span class="s1">'currentState'</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job</span><span class="p">:</span>
<span class="k">if</span> <span class="s1">'JOB_STATE_DONE'</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job</span><span class="p">[</span><span class="s1">'currentState'</span><span class="p">]:</span>
<span class="k">return</span> <span class="kc">True</span>
+ <span class="k">elif</span> <span class="s1">'JOB_STATE_RUNNING'</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job</span><span class="p">[</span><span class="s1">'currentState'</span><span class="p">]</span> <span class="ow">and</span> \
+ <span class="s1">'JOB_TYPE_STREAMING'</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job</span><span class="p">[</span><span class="s1">'type'</span><span class="p">]:</span>
+ <span class="k">return</span> <span class="kc">True</span>
<span class="k">elif</span> <span class="s1">'JOB_STATE_FAILED'</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job</span><span class="p">[</span><span class="s1">'currentState'</span><span class="p">]:</span>
<span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span><span class="s2">"Google Cloud Dataflow job </span><span class="si">{}</span><span class="s2"> has failed."</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_job</span><span class="p">[</span><span class="s1">'name'</span><span class="p">]))</span>
@@ -239,7 +265,7 @@
<span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span><span class="s2">"Google Cloud Dataflow job </span><span class="si">{}</span><span class="s2"> was cancelled."</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_job</span><span class="p">[</span><span class="s1">'name'</span><span class="p">]))</span>
<span class="k">elif</span> <span class="s1">'JOB_STATE_RUNNING'</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job</span><span class="p">[</span><span class="s1">'currentState'</span><span class="p">]:</span>
- <span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="mi">10</span><span class="p">)</span>
+ <span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_poll_sleep</span><span class="p">)</span>
<span class="k">elif</span> <span class="s1">'JOB_STATE_PENDING'</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job</span><span class="p">[</span><span class="s1">'currentState'</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>
@@ -258,13 +284,21 @@
<span class="k">class</span> <span class="nc">_Dataflow</span><span class="p">(</span><span class="n">LoggingMixin</span><span class="p">):</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">cmd</span><span class="p">):</span>
- <span class="bp">self</span><span class="o">.</span><span class="n">_proc</span> <span class="o">=</span> <span class="n">subprocess</span><span class="o">.</span><span class="n">Popen</span><span class="p">(</span><span class="n">cmd</span><span class="p">,</span> <span class="n">shell</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">stdout</span><span class="o">=</span><span class="n">subprocess</span><span class="o">.</span><span class="n">PIPE</span><span class="p">,</span>
- <span class="n">stderr</span><span class="o">=</span><span class="n">subprocess</span><span class="o">.</span><span class="n">PIPE</span><span class="p">)</span>
+ <span class="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">"Running command: </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="s1">' '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">cmd</span><span class="p">))</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_proc</span> <span class="o">=</span> <span class="n">subprocess</span><span class="o">.</span><span class="n">Popen</span><span class="p">(</span>
+ <span class="n">cmd</span><span class="p">,</span>
+ <span class="n">shell</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
+ <span class="n">stdout</span><span class="o">=</span><span class="n">subprocess</span><span class="o">.</span><span class="n">PIPE</span><span class="p">,</span>
+ <span class="n">stderr</span><span class="o">=</span><span class="n">subprocess</span><span class="o">.</span><span class="n">PIPE</span><span class="p">,</span>
+ <span class="n">close_fds</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_line</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">fd</span><span class="p">):</span>
<span class="k">if</span> <span class="n">fd</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">stderr</span><span class="o">.</span><span class="n">fileno</span><span class="p">():</span>
- <span class="n">line</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">stderr</span><span class="o">.</span><span class="n">readline</span><span class="p">()</span>
- <span class="k">return</span> <span class="n">line</span>
+ <span class="n">lines</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">stderr</span><span class="o">.</span><span class="n">readlines</span><span class="p">()</span>
+ <span class="k">for</span> <span class="n">line</span> <span class="ow">in</span> <span class="n">lines</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="n">line</span><span class="p">[:</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span>
+ <span class="k">if</span> <span class="n">lines</span><span class="p">:</span>
+ <span class="k">return</span> <span class="n">lines</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
<span class="k">if</span> <span class="n">fd</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">stdout</span><span class="o">.</span><span class="n">fileno</span><span class="p">():</span>
<span class="n">line</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">stdout</span><span class="o">.</span><span class="n">readline</span><span class="p">()</span>
<span class="k">return</span> <span class="n">line</span>
@@ -283,7 +317,8 @@
<span class="k">if</span> <span class="n">ret</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">for</span> <span class="n">fd</span> <span class="ow">in</span> <span class="n">ret</span><span class="p">[</span><span class="mi">0</span><span class="p">]:</span>
<span class="n">line</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_line</span><span class="p">(</span><span class="n">fd</span><span class="p">)</span>
- <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="n">line</span><span class="p">[:</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span>
+ <span class="k">if</span> <span class="n">line</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="n">line</span><span class="p">[:</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span>
<span class="k">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">"Waiting for DataFlow process to complete."</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">returncode</span> <span class="ow">is</span> <span class="ow">not</span> <span class="mi">0</span><span class="p">:</span>
@@ -295,7 +330,9 @@
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span>
<span class="n">gcp_conn_id</span><span class="o">=</span><span class="s1">'google_cloud_default'</span><span class="p">,</span>
- <span class="n">delegate_to</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
+ <span class="n">delegate_to</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">poll_sleep</span><span class="o">=</span><span class="mi">10</span><span class="p">):</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">poll_sleep</span> <span class="o">=</span> <span class="n">poll_sleep</span>
<span class="nb">super</span><span class="p">(</span><span class="n">DataFlowHook</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">gcp_conn_id</span><span class="p">,</span> <span class="n">delegate_to</span><span class="p">)</span>
<div class="viewcode-block" id="DataFlowHook.get_conn"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcp_dataflow_hook.DataFlowHook.get_conn">[docs]</a> <span class="k">def</span> <span class="nf">get_conn</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
@@ -305,30 +342,95 @@
<span class="n">http_authorized</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_authorize</span><span class="p">()</span>
<span class="k">return</span> <span class="n">build</span><span class="p">(</span><span class="s1">'dataflow'</span><span class="p">,</span> <span class="s1">'v1b3'</span><span class="p">,</span> <span class="n">http</span><span class="o">=</span><span class="n">http_authorized</span><span class="p">)</span></div>
- <span class="k">def</span> <span class="nf">_start_dataflow</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">task_id</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">dataflow</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">command_prefix</span><span class="p">):</span>
- <span class="n">cmd</span> <span class="o">=</span> <span class="n">command_prefix</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">_build_cmd</span><span class="p">(</span><span class="n">task_id</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">dataflow</span><span class="p">)</span>
+ <span class="k">def</span> <span class="nf">_start_dataflow</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">task_id</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span>
+ <span class="n">command_prefix</span><span class="p">,</span> <span class="n">label_formatter</span><span class="p">):</span>
+ <span class="n">variables</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set_variables</span><span class="p">(</span><span class="n">variables</span><span class="p">)</span>
+ <span class="n">cmd</span> <span class="o">=</span> <span class="n">command_prefix</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">_build_cmd</span><span class="p">(</span><span class="n">task_id</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span>
+ <span class="n">label_formatter</span><span class="p">)</span>
<span class="n">_Dataflow</span><span class="p">(</span><span class="n">cmd</span><span class="p">)</span><span class="o">.</span><span class="n">wait_for_done</span><span class="p">()</span>
- <span class="n">_DataflowJob</span><span class="p">(</span>
- <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">(),</span> <span class="n">variables</span><span class="p">[</span><span class="s1">'project'</span><span class="p">],</span> <span class="n">name</span><span class="p">)</span><span class="o">.</span><span class="n">wait_for_done</span><span class="p">()</span>
+ <span class="n">_DataflowJob</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">(),</span> <span class="n">variables</span><span class="p">[</span><span class="s1">'project'</span><span class="p">],</span> <span class="n">name</span><span class="p">,</span>
+ <span class="n">variables</span><span class="p">[</span><span class="s1">'region'</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">poll_sleep</span><span class="p">)</span><span class="o">.</span><span class="n">wait_for_done</span><span class="p">()</span>
- <span class="k">def</span> <span class="nf">start_java_dataflow</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">task_id</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">dataflow</span><span class="p">):</span>
- <span class="n">name</span> <span class="o">=</span> <span class="n">task_id</span> <span class="o">+</span> <span class="s2">"-"</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">uuid</span><span class="o">.</span><span class="n">uuid1</span><span class="p">())[:</span><span class="mi">8</span><span class="p">]</span>
+ <span class="nd">@staticmethod</span>
+ <span class="k">def</span> <span class="nf">_set_variables</span><span class="p">(</span><span class="n">variables</span><span class="p">):</span>
+ <span class="k">if</span> <span class="n">variables</span><span class="p">[</span><span class="s1">'project'</span><span class="p">]</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
+ <span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span><span class="s1">'Project not specified'</span><span class="p">)</span>
+ <span class="k">if</span> <span class="s1">'region'</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">variables</span><span class="o">.</span><span class="n">keys</span><span class="p">():</span>
+ <span class="n">variables</span><span class="p">[</span><span class="s1">'region'</span><span class="p">]</span> <span class="o">=</span> <span class="n">DEFAULT_DATAFLOW_LOCATION</span>
+ <span class="k">return</span> <span class="n">variables</span>
+
+ <span class="k">def</span> <span class="nf">start_java_dataflow</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">task_id</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">dataflow</span><span class="p">,</span> <span class="n">job_class</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">append_job_name</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
+ <span class="k">if</span> <span class="n">append_job_name</span><span class="p">:</span>
+ <span class="n">name</span> <span class="o">=</span> <span class="n">task_id</span> <span class="o">+</span> <span class="s2">"-"</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">uuid</span><span class="o">.</span><span class="n">uuid1</span><span class="p">())[:</span><span class="mi">8</span><span class="p">]</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="n">name</span> <span class="o">=</span> <span class="n">task_id</span>
<span class="n">variables</span><span class="p">[</span><span class="s1">'jobName'</span><span class="p">]</span> <span class="o">=</span> <span class="n">name</span>
- <span class="bp">self</span><span class="o">.</span><span class="n">_start_dataflow</span><span class="p">(</span>
- <span class="n">task_id</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">dataflow</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="p">[</span><span class="s2">"java"</span><span class="p">,</span> <span class="s2">"-jar"</span><span class="p">])</span>
- <span class="k">def</span> <span class="nf">start_python_dataflow</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">task_id</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">dataflow</span><span class="p">,</span> <span class="n">py_options</span><span class="p">):</span>
- <span class="n">name</span> <span class="o">=</span> <span class="n">task_id</span> <span class="o">+</span> <span class="s2">"-"</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">uuid</span><span class="o">.</span><span class="n">uuid1</span><span class="p">())[:</span><span class="mi">8</span><span class="p">]</span>
- <span class="n">variables</span><span class="p">[</span><span class="s2">"job_name"</span><span class="p">]</span> <span class="o">=</span> <span class="n">name</span>
- <span class="bp">self</span><span class="o">.</span><span class="n">_start_dataflow</span><span class="p">(</span>
- <span class="n">task_id</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">dataflow</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="p">[</span><span class="s2">"python"</span><span class="p">]</span> <span class="o">+</span> <span class="n">py_options</span><span class="p">)</span>
-
- <span class="k">def</span> <span class="nf">_build_cmd</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">task_id</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">dataflow</span><span class="p">):</span>
- <span class="n">command</span> <span class="o">=</span> <span class="p">[</span><span class="n">dataflow</span><span class="p">,</span> <span class="s2">"--runner=DataflowRunner"</span><span class="p">]</span>
+ <span class="k">def</span> <span class="nf">label_formatter</span><span class="p">(</span><span class="n">labels_dict</span><span class="p">):</span>
+ <span class="k">return</span> <span class="p">[</span><span class="s1">'--labels=</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
+ <span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="n">labels_dict</span><span class="p">)</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">' '</span><span class="p">,</span> <span class="s1">''</span><span class="p">))]</span>
+ <span class="n">command_prefix</span> <span class="o">=</span> <span class="p">([</span><span class="s2">"java"</span><span class="p">,</span> <span class="s2">"-cp"</span><span class="p">,</span> <span class="n">dataflow</span><span class="p">,</span> <span class="n">job_class</span><span class="p">]</span> <span class="k">if</span> <span class="n">job_class</span>
+ <span class="k">else</span> <span class="p">[</span><span class="s2">"java"</span><span class="p">,</span> <span class="s2">"-jar"</span><span class="p">,</span> <span class="n">dataflow</span><span class="p">])</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_start_dataflow</span><span class="p">(</span><span class="n">task_id</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span>
+ <span class="n">command_prefix</span><span class="p">,</span> <span class="n">label_formatter</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">start_template_dataflow</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">task_id</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">parameters</span><span class="p">,</span> <span class="n">dataflow_template</span><span class="p">,</span>
+ <span class="n">append_job_name</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
+ <span class="k">if</span> <span class="n">append_job_name</span><span class="p">:</span>
+ <span class="n">name</span> <span class="o">=</span> <span class="n">task_id</span> <span class="o">+</span> <span class="s2">"-"</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">uuid</span><span class="o">.</span><span class="n">uuid1</span><span class="p">())[:</span><span class="mi">8</span><span class="p">]</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="n">name</span> <span class="o">=</span> <span class="n">task_id</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_start_template_dataflow</span><span class="p">(</span>
+ <span class="n">name</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">parameters</span><span class="p">,</span> <span class="n">dataflow_template</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">start_python_dataflow</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">task_id</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">dataflow</span><span class="p">,</span> <span class="n">py_options</span><span class="p">,</span>
+ <span class="n">append_job_name</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
+ <span class="k">if</span> <span class="n">append_job_name</span><span class="p">:</span>
+ <span class="n">name</span> <span class="o">=</span> <span class="n">task_id</span> <span class="o">+</span> <span class="s2">"-"</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">uuid</span><span class="o">.</span><span class="n">uuid1</span><span class="p">())[:</span><span class="mi">8</span><span class="p">]</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="n">name</span> <span class="o">=</span> <span class="n">task_id</span>
+ <span class="n">variables</span><span class="p">[</span><span class="s1">'job_name'</span><span class="p">]</span> <span class="o">=</span> <span class="n">name</span>
+
+ <span class="k">def</span> <span class="nf">label_formatter</span><span class="p">(</span><span class="n">labels_dict</span><span class="p">):</span>
+ <span class="k">return</span> <span class="p">[</span><span class="s1">'--labels=</span><span class="si">{}</span><span class="s1">=</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">key</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span>
+ <span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="n">labels_dict</span><span class="o">.</span><span class="n">items</span><span class="p">()]</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_start_dataflow</span><span class="p">(</span><span class="n">task_id</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span>
+ <span class="p">[</span><span class="s2">"python"</span><span class="p">]</span> <span class="o">+</span> <span class="n">py_options</span> <span class="o">+</span> <span class="p">[</span><span class="n">dataflow</span><span class="p">],</span>
+ <span class="n">label_formatter</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">_build_cmd</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">task_id</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">label_formatter</span><span class="p">):</span>
+ <span class="n">command</span> <span class="o">=</span> <span class="p">[</span><span class="s2">"--runner=DataflowRunner"</span><span class="p">]</span>
<span class="k">if</span> <span class="n">variables</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
- <span class="k">for</span> <span class="n">attr</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="n">variables</span><span class="o">.</span><span class="n">iteritems</span><span class="p">():</span>
- <span class="n">command</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s2">"--"</span> <span class="o">+</span> <span class="n">attr</span> <span class="o">+</span> <span class="s2">"="</span> <span class="o">+</span> <span class="n">value</span><span class="p">)</span>
- <span class="k">return</span> <span class="n">command</span></div>
+ <span class="k">for</span> <span class="n">attr</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="n">variables</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
+ <span class="k">if</span> <span class="n">attr</span> <span class="o">==</span> <span class="s1">'labels'</span><span class="p">:</span>
+ <span class="n">command</span> <span class="o">+=</span> <span class="n">label_formatter</span><span class="p">(</span><span class="n">value</span><span class="p">)</span>
+ <span class="k">elif</span> <span class="n">value</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">value</span><span class="o">.</span><span class="fm">__len__</span><span class="p">()</span> <span class="o"><</span> <span class="mi">1</span><span class="p">:</span>
+ <span class="n">command</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s2">"--"</span> <span class="o">+</span> <span class="n">attr</span><span class="p">)</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="n">command</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s2">"--"</span> <span class="o">+</span> <span class="n">attr</span> <span class="o">+</span> <span class="s2">"="</span> <span class="o">+</span> <span class="n">value</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">command</span>
+
+ <span class="k">def</span> <span class="nf">_start_template_dataflow</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">parameters</span><span class="p">,</span> <span class="n">dataflow_template</span><span class="p">):</span>
+ <span class="c1"># Builds RuntimeEnvironment from variables dictionary</span>
+ <span class="c1"># https://cloud.google.com/dataflow/docs/reference/rest/v1b3/RuntimeEnvironment</span>
+ <span class="n">environment</span> <span class="o">=</span> <span class="p">{}</span>
+ <span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'maxWorkers'</span><span class="p">,</span> <span class="s1">'zone'</span><span class="p">,</span> <span class="s1">'serviceAccountEmail'</span><span class="p">,</span> <span class="s1">'tempLocation'</span><span class="p">,</span>
+ <span class="s1">'bypassTempDirValidation'</span><span class="p">,</span> <span class="s1">'machineType'</span><span class="p">]:</span>
+ <span class="k">if</span> <span class="n">key</span> <span class="ow">in</span> <span class="n">variables</span><span class="p">:</span>
+ <span class="n">environment</span><span class="o">.</span><span class="n">update</span><span class="p">({</span><span class="n">key</span><span class="p">:</span> <span class="n">variables</span><span class="p">[</span><span class="n">key</span><span class="p">]})</span>
+ <span class="n">body</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"jobName"</span><span class="p">:</span> <span class="n">name</span><span class="p">,</span>
+ <span class="s2">"parameters"</span><span class="p">:</span> <span class="n">parameters</span><span class="p">,</span>
+ <span class="s2">"environment"</span><span class="p">:</span> <span class="n">environment</span><span class="p">}</span>
+ <span class="n">service</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span>
+ <span class="n">request</span> <span class="o">=</span> <span class="n">service</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">templates</span><span class="p">()</span><span class="o">.</span><span class="n">launch</span><span class="p">(</span><span class="n">projectId</span><span class="o">=</span><span class="n">variables</span><span class="p">[</span><span class="s1">'project'</span><span class="p">],</span>
+ <span class="n">gcsPath</span><span class="o">=</span><span class="n">dataflow_template</span><span class="p">,</span>
+ <span class="n">body</span><span class="o">=</span><span class="n">body</span><span class="p">)</span>
+ <span class="n">response</span> <span class="o">=</span> <span class="n">request</span><span class="o">.</span><span class="n">execute</span><span class="p">()</span>
+ <span class="n">variables</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set_variables</span><span class="p">(</span><span class="n">variables</span><span class="p">)</span>
+ <span class="n">_DataflowJob</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">(),</span> <span class="n">variables</span><span class="p">[</span><span class="s1">'project'</span><span class="p">],</span> <span class="n">name</span><span class="p">,</span> <span class="n">variables</span><span class="p">[</span><span class="s1">'region'</span><span class="p">],</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">poll_sleep</span><span class="p">)</span><span class="o">.</span><span class="n">wait_for_done</span><span class="p">()</span>
+ <span class="k">return</span> <span class="n">response</span></div>
</pre></div>
</div>